#ironman — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #ironman, aggregated by home.social.
-
https://www.europesays.com/sk/68976/ Čo keby sa superhrdinovia prihlásili do Mama, ožeň ma? #Avengers #batman #BruceWayne #DC #Entertainment #film #Filmy #IronMan #ľudia #MamaOžeňMa #Marvel #PeterParker #RealityShow #SK #Slovak #Slovakia #Slovenčina #Slovensko #SpiderMan #TonyStark #VKine #Zábava #zaujimavosti
-
Movie TV Tech Geeks #MovieFeatures #IronMan #MCU #Disney 18 Years Later, Disney's Action Sci-Fi Is Taking Over the World Once Again http://dlvr.it/TSW5mP
-
creates semantic nodes and clusters 2016 #IRONMAN 70 3 #WORLD #CHAMPIONSHIP chatgpt.com?prompt=Analy... #PETAL #ALBUM multi-search-tag-explorer.aepiot.com/advanced-sea... AÉPIOT: INDEPENDENT SEMANTIC WEB 4.0 INFRASTRUCTURE (EST. 2009): headlines-world.com
ChatGPT -
creates semantic nodes and clusters 2016 #IRONMAN 70 3 #WORLD #CHAMPIONSHIP chatgpt.com?prompt=Analy... #PETAL #ALBUM multi-search-tag-explorer.aepiot.com/advanced-sea... AÉPIOT: INDEPENDENT SEMANTIC WEB 4.0 INFRASTRUCTURE (EST. 2009): headlines-world.com
ChatGPT -
130 - Iron Man Annual #4 - 5/10/1977
I still have a soft spot for the Champions aka the "Miscellaneous Team."
Cover by Al Milgrom. Interiors by Bill Mantlo & George Tuska.
-
130 - Iron Man Annual #4 - 5/10/1977
I still have a soft spot for the Champions aka the "Miscellaneous Team."
Cover by Al Milgrom. Interiors by Bill Mantlo & George Tuska.
-
130 - Iron Man Annual #4 - 5/10/1977
I still have a soft spot for the Champions aka the "Miscellaneous Team."
Cover by Al Milgrom. Interiors by Bill Mantlo & George Tuska.
-
Be@rbrick #Marvel Studios Happy Kuji: Iron Man Mark 3 #1 *Sealed* brought to you by the #PlastiqueBoutique https://plastiqueboutique.com/product/berbrick-marvel-studios-happy-kuji-iron-man-mark-3-1-sealed/?utm_source=mastodon&utm_medium=social&utm_campaign=ReviveOldPost #AvengersToy #AvengersCollector #AvengersCollection #AvengersFigures #IronManToys #Toys #IronManCollector #IronManFigures #IronManToy #AvengersFigure #AvengersCollections #IronManCollections #IronManDisplay #IronMan #IronManCollectors #IronManCollection #AvengersCollectors #Avengers #IronManFigure
-
Movie TV Tech Geeks #MovieNews #RobertDowneyJr #IronMan #IronMan2 Disney's Franchise-Starting Sci-Fi Saga Is a Sudden Streaming Hit 18 Years Later http://dlvr.it/TSS7Rt
-
Train Smarter for Your Ironman with EnduraCoach — The AI Companion That Actually Delivers
A few months ago, I finished a long ride—just over 100 miles, solid climbing, felt strong the entire way. The kind of session that makes you think, I’m on track.
The next week, I pushed again. Then again.
Nothing dramatic—just a bit more volume, a bit more intensity. Exactly what most self-coached athletes do when things feel good.
Two weeks later, I was flat. Not injured. Not sick. Just… off. Power was down, runs felt heavy, motivation dipped. The frustrating kind of fatigue where nothing is clearly wrong—but nothing is clearly right either.
When I looked back, the pattern was obvious:
- I had increased load too quickly
- Skipped a proper recovery week
- Let “feeling good” override structure
What’s worse: all the data was there.
Garmin had it.
The workouts were logged.
The signals existed.I just didn’t have a system that could connect the dots, enforce discipline, and still adapt intelligently.
That’s the gap.
Most tools today fall into two extremes:
- Static plans that ignore what you actually did
- “AI coaching” that sounds smart but you can’t really trust
I wanted something in between:
A system that keeps me honest on the fundamentals—while still helping me think, adapt, and improve.
That’s where EnduraCoach started.
The bet: coaching that feels intelligent—without gambling on math.
EnduraCoach is an AI-assisted Ironman training app built on a simple premise:
the model does not control your training plan.Instead, the system splits responsibilities:
- A deterministic engine owns load, progression, and structure
- The LLM handles conversation, explanation, and suggestions
- The user explicitly approves any changes
That separation isn’t academic—it’s the difference between something that sounds smart and something you can actually trust with your body.
Why not let the model run everything?
Because LLMs are excellent at language and context—and unreliable (or just less reliable) at consistent, safe, structured planning. In the (near) future, that might change and we can ‘give it all’ to the LLMs. But for now, let’s keep this part out of it.
Training plans require:
- Repeatability: same inputs → same outputs
- Bounded risk: no surprise spikes in load. We don’t want to get injured.
- Testability: you can verify behavior before doing a session.
So there’s a hard rule in the system:
The LLM never owns training math.
That constraint drives everything else.
The Core System
Think of EnduraCoach as three cooperating layers:
1. Deterministic Training Engine (the source of truth)
This is where the real coaching logic lives.
- Structured phases: base → build → peak → taper
- Recovery every 4th week
- Guardrails:
- Intensity step <= +1 zone for beginner/intermediate, +2 for advanced
- Weekly volume increase <= 15% for advanced cyclists, 12% intermediate, 10% beginner; 8% for all swim and run sessions
- Mandatory recovery week every 4 weeks
- Preset distributions by race distance
- Monday-aligned week grid (so UI and logic never drift)
This is intentionally conservative.
You can reason about it.
You can test it – You can trust it.2. Conversational Layer – LLM as advisor, not authority
The coach experience is powered by Google Gemini via
@google/genai.But it operates under strict constraints:
- No full chat history dumping
- A single structured memory state per user
- Fixed prompt structure:
- athlete profile
- goal
- current phase
- last week summary
- current week snapshot
- user message
This keeps responses:
- consistent
- grounded
- cheap (token-wise)
- actually useful
The model proposes ideas—it does not execute them.
3. Governance Loop: propose → approve → apply
This is the most important product decision.
When the model suggests a change:
- It generates a proposal
- The backend converts it into a validated diff via the engine
- The diff is stored as pending
- The user must explicitly approve
- Only then is it applied (transactionally, with an allowlist)
No silent edits. No hidden mutations.
User agency is not a feature—it’s the control system.
Grounding in Reality: Garmin Paste Import
Instead of starting with API integrations, EnduraCoach takes a faster path:
- Users paste activity data from Garmin Connect
- A tolerant parser extracts metrics (time, distance, HR, power, TSS)
- Activities are matched to planned workouts (±1 day, same sport)
From there:
- workouts are marked completed / missed / extra
- recent stats (14-day window) are computed
- a simple fatigue signal (e.g., HR drift) is added to memory
This creates a feedback loop:
Plan → Train → Import → Reconcile → Adjust
No brittle integrations required to get real value.
Product Decisions That Actually Matter
Authentication: fast dev, safe prod
- Google OAuth in production
- Dev login for local/staging only
- UI removes dev login in production builds
You move fast without weakening security.
Structured onboarding (not “tell me about yourself”)
A 4-step flow captures:
- goal
- experience
- biometrics
- constraints
Why? Because the engine needs typed inputs—not paragraphs.
Markdown coach responses
- Clean formatting (lists, emphasis)
- Safer rendering (user input stays plain)
Small detail, big UX upgrade.
Graceful degradation
No Gemini key?
- The system still runs
- Chat falls back to deterministic responses
Zero setup friction.
Infrastructure: deliberately boring
- Frontend: React + Vite + Tailwind
- Backend: Node + Express
- DB: SQLite (single file, backed up)
- Auth: Passport + sessions
- Deploy: Docker on **Fly.io
Why this stack?
Because complexity is the enemy of iteration—especially in v1.
A subtle but important detail
The app serves both:
- API routes (
/plan,/auth, etc.) - SPA routes (also
/planin the UI)
The server distinguishes based on
Accept: text/html.Without this, routing breaks in non-obvious ways.
What’s intentionally missing in the MVP
Not everything belongs in v1:
- Google Calendar sync
- advanced CTL/ATL analytics
- strength training templates
These are useful—but not critical.
Shipping them early adds surface area and support burden without strengthening the core loop.
The Real Product
EnduraCoach isn’t “AI coaching.”
It’s a system where:
- Rules ensure safety and consistency
- AI adds intelligence and usability
- The user stays in control
That combination matters.
Because in endurance training, credibility doesn’t come from elegant language—it comes from predictable progression and transparent decisions.
Bottom line
Most AI products ask: “What can the model do?”
This one asks:
“What should the model should not be allowed to do?”
That constraint is the product.
And it’s the reason it works.Rate this:
#AI #ironman #Sport #tools #webapp -
Train Smarter for Your Ironman with EnduraCoach — The AI Companion That Actually Delivers
A few months ago, I finished a long ride—just over 100 miles, solid climbing, felt strong the entire way. The kind of session that makes you think, I’m on track.
The next week, I pushed again. Then again.
Nothing dramatic—just a bit more volume, a bit more intensity. Exactly what most self-coached athletes do when things feel good.
Two weeks later, I was flat. Not injured. Not sick. Just… off. Power was down, runs felt heavy, motivation dipped. The frustrating kind of fatigue where nothing is clearly wrong—but nothing is clearly right either.
When I looked back, the pattern was obvious:
- I had increased load too quickly
- Skipped a proper recovery week
- Let “feeling good” override structure
What’s worse: all the data was there.
Garmin had it.
The workouts were logged.
The signals existed.I just didn’t have a system that could connect the dots, enforce discipline, and still adapt intelligently.
That’s the gap.
Most tools today fall into two extremes:
- Static plans that ignore what you actually did
- “AI coaching” that sounds smart but you can’t really trust
I wanted something in between:
A system that keeps me honest on the fundamentals—while still helping me think, adapt, and improve.
That’s where EnduraCoach started.
The bet: coaching that feels intelligent—without gambling on math.
EnduraCoach is an AI-assisted Ironman training app built on a simple premise:
the model does not control your training plan.Instead, the system splits responsibilities:
- A deterministic engine owns load, progression, and structure
- The LLM handles conversation, explanation, and suggestions
- The user explicitly approves any changes
That separation isn’t academic—it’s the difference between something that sounds smart and something you can actually trust with your body.
Why not let the model run everything?
Because LLMs are excellent at language and context—and unreliable (or just less reliable) at consistent, safe, structured planning. In the (near) future, that might change and we can ‘give it all’ to the LLMs. But for now, let’s keep this part out of it.
Training plans require:
- Repeatability: same inputs → same outputs
- Bounded risk: no surprise spikes in load. We don’t want to get injured.
- Testability: you can verify behavior before doing a session.
So there’s a hard rule in the system:
The LLM never owns training math.
That constraint drives everything else.
The Core System
Think of EnduraCoach as three cooperating layers:
1. Deterministic Training Engine (the source of truth)
This is where the real coaching logic lives.
- Structured phases: base → build → peak → taper
- Recovery every 4th week
- Guardrails:
- Intensity step <= +1 zone for beginner/intermediate, +2 for advanced
- Weekly volume increase <= 15% for advanced cyclists, 12% intermediate, 10% beginner; 8% for all swim and run sessions
- Mandatory recovery week every 4 weeks
- Preset distributions by race distance
- Monday-aligned week grid (so UI and logic never drift)
This is intentionally conservative.
You can reason about it.
You can test it – You can trust it.2. Conversational Layer – LLM as advisor, not authority
The coach experience is powered by Google Gemini via
@google/genai.But it operates under strict constraints:
- No full chat history dumping
- A single structured memory state per user
- Fixed prompt structure:
- athlete profile
- goal
- current phase
- last week summary
- current week snapshot
- user message
This keeps responses:
- consistent
- grounded
- cheap (token-wise)
- actually useful
The model proposes ideas—it does not execute them.
3. Governance Loop: propose → approve → apply
This is the most important product decision.
When the model suggests a change:
- It generates a proposal
- The backend converts it into a validated diff via the engine
- The diff is stored as pending
- The user must explicitly approve
- Only then is it applied (transactionally, with an allowlist)
No silent edits. No hidden mutations.
User agency is not a feature—it’s the control system.
Grounding in Reality: Garmin Paste Import
Instead of starting with API integrations, EnduraCoach takes a faster path:
- Users paste activity data from Garmin Connect
- A tolerant parser extracts metrics (time, distance, HR, power, TSS)
- Activities are matched to planned workouts (±1 day, same sport)
From there:
- workouts are marked completed / missed / extra
- recent stats (14-day window) are computed
- a simple fatigue signal (e.g., HR drift) is added to memory
This creates a feedback loop:
Plan → Train → Import → Reconcile → Adjust
No brittle integrations required to get real value.
Product Decisions That Actually Matter
Authentication: fast dev, safe prod
- Google OAuth in production
- Dev login for local/staging only
- UI removes dev login in production builds
You move fast without weakening security.
Structured onboarding (not “tell me about yourself”)
A 4-step flow captures:
- goal
- experience
- biometrics
- constraints
Why? Because the engine needs typed inputs—not paragraphs.
Markdown coach responses
- Clean formatting (lists, emphasis)
- Safer rendering (user input stays plain)
Small detail, big UX upgrade.
Graceful degradation
No Gemini key?
- The system still runs
- Chat falls back to deterministic responses
Zero setup friction.
Infrastructure: deliberately boring
- Frontend: React + Vite + Tailwind
- Backend: Node + Express
- DB: SQLite (single file, backed up)
- Auth: Passport + sessions
- Deploy: Docker on **Fly.io
Why this stack?
Because complexity is the enemy of iteration—especially in v1.
A subtle but important detail
The app serves both:
- API routes (
/plan,/auth, etc.) - SPA routes (also
/planin the UI)
The server distinguishes based on
Accept: text/html.Without this, routing breaks in non-obvious ways.
What’s intentionally missing in the MVP
Not everything belongs in v1:
- Google Calendar sync
- advanced CTL/ATL analytics
- strength training templates
These are useful—but not critical.
Shipping them early adds surface area and support burden without strengthening the core loop.
The Real Product
EnduraCoach isn’t “AI coaching.”
It’s a system where:
- Rules ensure safety and consistency
- AI adds intelligence and usability
- The user stays in control
That combination matters.
Because in endurance training, credibility doesn’t come from elegant language—it comes from predictable progression and transparent decisions.
Bottom line
Most AI products ask: “What can the model do?”
This one asks:
“What should the model should not be allowed to do?”
That constraint is the product.
#AI #ironman #Sport #tools #webapp
And it’s the reason it works. -
Train Smarter for Your Ironman with EnduraCoach — The AI Companion That Actually Delivers
A few months ago, I finished a long ride—just over 100 miles, solid climbing, felt strong the entire way. The kind of session that makes you think, I’m on track.
The next week, I pushed again. Then again.
Nothing dramatic—just a bit more volume, a bit more intensity. Exactly what most self-coached athletes do when things feel good.
Two weeks later, I was flat. Not injured. Not sick. Just… off. Power was down, runs felt heavy, motivation dipped. The frustrating kind of fatigue where nothing is clearly wrong—but nothing is clearly right either.
When I looked back, the pattern was obvious:
- I had increased load too quickly
- Skipped a proper recovery week
- Let “feeling good” override structure
What’s worse: all the data was there.
Garmin had it.
The workouts were logged.
The signals existed.I just didn’t have a system that could connect the dots, enforce discipline, and still adapt intelligently.
That’s the gap.
Most tools today fall into two extremes:
- Static plans that ignore what you actually did
- “AI coaching” that sounds smart but you can’t really trust
I wanted something in between:
A system that keeps me honest on the fundamentals—while still helping me think, adapt, and improve.
That’s where EnduraCoach started.
The bet: coaching that feels intelligent—without gambling on math.
EnduraCoach is an AI-assisted Ironman training app built on a simple premise:
the model does not control your training plan.Instead, the system splits responsibilities:
- A deterministic engine owns load, progression, and structure
- The LLM handles conversation, explanation, and suggestions
- The user explicitly approves any changes
That separation isn’t academic—it’s the difference between something that sounds smart and something you can actually trust with your body.
Why not let the model run everything?
Because LLMs are excellent at language and context—and unreliable (or just less reliable) at consistent, safe, structured planning. In the (near) future, that might change and we can ‘give it all’ to the LLMs. But for now, let’s keep this part out of it.
Training plans require:
- Repeatability: same inputs → same outputs
- Bounded risk: no surprise spikes in load. We don’t want to get injured.
- Testability: you can verify behavior before doing a session.
So there’s a hard rule in the system:
The LLM never owns training math.
That constraint drives everything else.
The Core System
Think of EnduraCoach as three cooperating layers:
1. Deterministic Training Engine (the source of truth)
This is where the real coaching logic lives.
- Structured phases: base → build → peak → taper
- Recovery every 4th week
- Guardrails:
- Intensity step <= +1 zone for beginner/intermediate, +2 for advanced
- Weekly volume increase <= 15% for advanced cyclists, 12% intermediate, 10% beginner; 8% for all swim and run sessions
- Mandatory recovery week every 4 weeks
- Preset distributions by race distance
- Monday-aligned week grid (so UI and logic never drift)
This is intentionally conservative.
You can reason about it.
You can test it – You can trust it.2. Conversational Layer – LLM as advisor, not authority
The coach experience is powered by Google Gemini via
@google/genai.But it operates under strict constraints:
- No full chat history dumping
- A single structured memory state per user
- Fixed prompt structure:
- athlete profile
- goal
- current phase
- last week summary
- current week snapshot
- user message
This keeps responses:
- consistent
- grounded
- cheap (token-wise)
- actually useful
The model proposes ideas—it does not execute them.
3. Governance Loop: propose → approve → apply
This is the most important product decision.
When the model suggests a change:
- It generates a proposal
- The backend converts it into a validated diff via the engine
- The diff is stored as pending
- The user must explicitly approve
- Only then is it applied (transactionally, with an allowlist)
No silent edits. No hidden mutations.
User agency is not a feature—it’s the control system.
Grounding in Reality: Garmin Paste Import
Instead of starting with API integrations, EnduraCoach takes a faster path:
- Users paste activity data from Garmin Connect
- A tolerant parser extracts metrics (time, distance, HR, power, TSS)
- Activities are matched to planned workouts (±1 day, same sport)
From there:
- workouts are marked completed / missed / extra
- recent stats (14-day window) are computed
- a simple fatigue signal (e.g., HR drift) is added to memory
This creates a feedback loop:
Plan → Train → Import → Reconcile → Adjust
No brittle integrations required to get real value.
Product Decisions That Actually Matter
Authentication: fast dev, safe prod
- Google OAuth in production
- Dev login for local/staging only
- UI removes dev login in production builds
You move fast without weakening security.
Structured onboarding (not “tell me about yourself”)
A 4-step flow captures:
- goal
- experience
- biometrics
- constraints
Why? Because the engine needs typed inputs—not paragraphs.
Markdown coach responses
- Clean formatting (lists, emphasis)
- Safer rendering (user input stays plain)
Small detail, big UX upgrade.
Graceful degradation
No Gemini key?
- The system still runs
- Chat falls back to deterministic responses
Zero setup friction.
Infrastructure: deliberately boring
- Frontend: React + Vite + Tailwind
- Backend: Node + Express
- DB: SQLite (single file, backed up)
- Auth: Passport + sessions
- Deploy: Docker on **Fly.io
Why this stack?
Because complexity is the enemy of iteration—especially in v1.
A subtle but important detail
The app serves both:
- API routes (
/plan,/auth, etc.) - SPA routes (also
/planin the UI)
The server distinguishes based on
Accept: text/html.Without this, routing breaks in non-obvious ways.
What’s intentionally missing in the MVP
Not everything belongs in v1:
- Google Calendar sync
- advanced CTL/ATL analytics
- strength training templates
These are useful—but not critical.
Shipping them early adds surface area and support burden without strengthening the core loop.
The Real Product
EnduraCoach isn’t “AI coaching.”
It’s a system where:
- Rules ensure safety and consistency
- AI adds intelligence and usability
- The user stays in control
That combination matters.
Because in endurance training, credibility doesn’t come from elegant language—it comes from predictable progression and transparent decisions.
Bottom line
Most AI products ask: “What can the model do?”
This one asks:
“What should the model should not be allowed to do?”
That constraint is the product.
And it’s the reason it works.Rate this:
#AI #ironman #Sport #tools #webapp -
Train Smarter for Your Ironman with EnduraCoach — The AI Companion That Actually Delivers
A few months ago, I finished a long ride—just over 100 miles, solid climbing, felt strong the entire way. The kind of session that makes you think, I’m on track.
The next week, I pushed again. Then again.
Nothing dramatic—just a bit more volume, a bit more intensity. Exactly what most self-coached athletes do when things feel good.
Two weeks later, I was flat. Not injured. Not sick. Just… off. Power was down, runs felt heavy, motivation dipped. The frustrating kind of fatigue where nothing is clearly wrong—but nothing is clearly right either.
When I looked back, the pattern was obvious:
- I had increased load too quickly
- Skipped a proper recovery week
- Let “feeling good” override structure
What’s worse: all the data was there.
Garmin had it.
The workouts were logged.
The signals existed.I just didn’t have a system that could connect the dots, enforce discipline, and still adapt intelligently.
That’s the gap.
Most tools today fall into two extremes:
- Static plans that ignore what you actually did
- “AI coaching” that sounds smart but you can’t really trust
I wanted something in between:
A system that keeps me honest on the fundamentals—while still helping me think, adapt, and improve.
That’s where EnduraCoach started.
The bet: coaching that feels intelligent—without gambling on math.
EnduraCoach is an AI-assisted Ironman training app built on a simple premise:
the model does not control your training plan.Instead, the system splits responsibilities:
- A deterministic engine owns load, progression, and structure
- The LLM handles conversation, explanation, and suggestions
- The user explicitly approves any changes
That separation isn’t academic—it’s the difference between something that sounds smart and something you can actually trust with your body.
Why not let the model run everything?
Because LLMs are excellent at language and context—and unreliable (or just less reliable) at consistent, safe, structured planning. In the (near) future, that might change and we can ‘give it all’ to the LLMs. But for now, let’s keep this part out of it.
Training plans require:
- Repeatability: same inputs → same outputs
- Bounded risk: no surprise spikes in load. We don’t want to get injured.
- Testability: you can verify behavior before doing a session.
So there’s a hard rule in the system:
The LLM never owns training math.
That constraint drives everything else.
The Core System
Think of EnduraCoach as three cooperating layers:
1. Deterministic Training Engine (the source of truth)
This is where the real coaching logic lives.
- Structured phases: base → build → peak → taper
- Recovery every 4th week
- Guardrails:
- Intensity step <= +1 zone for beginner/intermediate, +2 for advanced
- Weekly volume increase <= 15% for advanced cyclists, 12% intermediate, 10% beginner; 8% for all swim and run sessions
- Mandatory recovery week every 4 weeks
- Preset distributions by race distance
- Monday-aligned week grid (so UI and logic never drift)
This is intentionally conservative.
You can reason about it.
You can test it – You can trust it.2. Conversational Layer – LLM as advisor, not authority
The coach experience is powered by Google Gemini via
@google/genai.But it operates under strict constraints:
- No full chat history dumping
- A single structured memory state per user
- Fixed prompt structure:
- athlete profile
- goal
- current phase
- last week summary
- current week snapshot
- user message
This keeps responses:
- consistent
- grounded
- cheap (token-wise)
- actually useful
The model proposes ideas—it does not execute them.
3. Governance Loop: propose → approve → apply
This is the most important product decision.
When the model suggests a change:
- It generates a proposal
- The backend converts it into a validated diff via the engine
- The diff is stored as pending
- The user must explicitly approve
- Only then is it applied (transactionally, with an allowlist)
No silent edits. No hidden mutations.
User agency is not a feature—it’s the control system.
Grounding in Reality: Garmin Paste Import
Instead of starting with API integrations, EnduraCoach takes a faster path:
- Users paste activity data from Garmin Connect
- A tolerant parser extracts metrics (time, distance, HR, power, TSS)
- Activities are matched to planned workouts (±1 day, same sport)
From there:
- workouts are marked completed / missed / extra
- recent stats (14-day window) are computed
- a simple fatigue signal (e.g., HR drift) is added to memory
This creates a feedback loop:
Plan → Train → Import → Reconcile → Adjust
No brittle integrations required to get real value.
Product Decisions That Actually Matter
Authentication: fast dev, safe prod
- Google OAuth in production
- Dev login for local/staging only
- UI removes dev login in production builds
You move fast without weakening security.
Structured onboarding (not “tell me about yourself”)
A 4-step flow captures:
- goal
- experience
- biometrics
- constraints
Why? Because the engine needs typed inputs—not paragraphs.
Markdown coach responses
- Clean formatting (lists, emphasis)
- Safer rendering (user input stays plain)
Small detail, big UX upgrade.
Graceful degradation
No Gemini key?
- The system still runs
- Chat falls back to deterministic responses
Zero setup friction.
Infrastructure: deliberately boring
- Frontend: React + Vite + Tailwind
- Backend: Node + Express
- DB: SQLite (single file, backed up)
- Auth: Passport + sessions
- Deploy: Docker on **Fly.io
Why this stack?
Because complexity is the enemy of iteration—especially in v1.
A subtle but important detail
The app serves both:
- API routes (
/plan,/auth, etc.) - SPA routes (also
/planin the UI)
The server distinguishes based on
Accept: text/html.Without this, routing breaks in non-obvious ways.
What’s intentionally missing in the MVP
Not everything belongs in v1:
- Google Calendar sync
- advanced CTL/ATL analytics
- strength training templates
These are useful—but not critical.
Shipping them early adds surface area and support burden without strengthening the core loop.
The Real Product
EnduraCoach isn’t “AI coaching.”
It’s a system where:
- Rules ensure safety and consistency
- AI adds intelligence and usability
- The user stays in control
That combination matters.
Because in endurance training, credibility doesn’t come from elegant language—it comes from predictable progression and transparent decisions.
Bottom line
Most AI products ask: “What can the model do?”
This one asks:
“What should the model should not be allowed to do?”
That constraint is the product.
And it’s the reason it works.Rate this:
#AI #ironman #Sport #tools #webapp -
Train Smarter for Your Ironman with EnduraCoach — The AI Companion That Actually Delivers
A few months ago, I finished a long ride—just over 100 miles, solid climbing, felt strong the entire way. The kind of session that makes you think, I’m on track.
The next week, I pushed again. Then again.
Nothing dramatic—just a bit more volume, a bit more intensity. Exactly what most self-coached athletes do when things feel good.
Two weeks later, I was flat. Not injured. Not sick. Just… off. Power was down, runs felt heavy, motivation dipped. The frustrating kind of fatigue where nothing is clearly wrong—but nothing is clearly right either.
When I looked back, the pattern was obvious:
- I had increased load too quickly
- Skipped a proper recovery week
- Let “feeling good” override structure
What’s worse: all the data was there.
Garmin had it.
The workouts were logged.
The signals existed.I just didn’t have a system that could connect the dots, enforce discipline, and still adapt intelligently.
That’s the gap.
Most tools today fall into two extremes:
- Static plans that ignore what you actually did
- “AI coaching” that sounds smart but you can’t really trust
I wanted something in between:
A system that keeps me honest on the fundamentals—while still helping me think, adapt, and improve.
That’s where EnduraCoach started.
The bet: coaching that feels intelligent—without gambling on math.
EnduraCoach is an AI-assisted Ironman training app built on a simple premise:
the model does not control your training plan.Instead, the system splits responsibilities:
- A deterministic engine owns load, progression, and structure
- The LLM handles conversation, explanation, and suggestions
- The user explicitly approves any changes
That separation isn’t academic—it’s the difference between something that sounds smart and something you can actually trust with your body.
Why not let the model run everything?
Because LLMs are excellent at language and context—and unreliable (or just less reliable) at consistent, safe, structured planning. In the (near) future, that might change and we can ‘give it all’ to the LLMs. But for now, let’s keep this part out of it.
Training plans require:
- Repeatability: same inputs → same outputs
- Bounded risk: no surprise spikes in load. We don’t want to get injured.
- Testability: you can verify behavior before doing a session.
So there’s a hard rule in the system:
The LLM never owns training math.
That constraint drives everything else.
The Core System
Think of EnduraCoach as three cooperating layers:
1. Deterministic Training Engine (the source of truth)
This is where the real coaching logic lives.
- Structured phases: base → build → peak → taper
- Recovery every 4th week
- Guardrails:
- Intensity step <= +1 zone for beginner/intermediate, +2 for advanced
- Weekly volume increase <= 15% for advanced cyclists, 12% intermediate, 10% beginner; 8% for all swim and run sessions
- Mandatory recovery week every 4 weeks
- Preset distributions by race distance
- Monday-aligned week grid (so UI and logic never drift)
This is intentionally conservative.
You can reason about it.
You can test it – You can trust it.2. Conversational Layer – LLM as advisor, not authority
The coach experience is powered by Google Gemini via
@google/genai.But it operates under strict constraints:
- No full chat history dumping
- A single structured memory state per user
- Fixed prompt structure:
- athlete profile
- goal
- current phase
- last week summary
- current week snapshot
- user message
This keeps responses:
- consistent
- grounded
- cheap (token-wise)
- actually useful
The model proposes ideas—it does not execute them.
3. Governance Loop: propose → approve → apply
This is the most important product decision.
When the model suggests a change:
- It generates a proposal
- The backend converts it into a validated diff via the engine
- The diff is stored as pending
- The user must explicitly approve
- Only then is it applied (transactionally, with an allowlist)
No silent edits. No hidden mutations.
User agency is not a feature—it’s the control system.
Grounding in Reality: Garmin Paste Import
Instead of starting with API integrations, EnduraCoach takes a faster path:
- Users paste activity data from Garmin Connect
- A tolerant parser extracts metrics (time, distance, HR, power, TSS)
- Activities are matched to planned workouts (±1 day, same sport)
From there:
- workouts are marked completed / missed / extra
- recent stats (14-day window) are computed
- a simple fatigue signal (e.g., HR drift) is added to memory
This creates a feedback loop:
Plan → Train → Import → Reconcile → Adjust
No brittle integrations required to get real value.
Product Decisions That Actually Matter
Authentication: fast dev, safe prod
- Google OAuth in production
- Dev login for local/staging only
- UI removes dev login in production builds
You move fast without weakening security.
Structured onboarding (not “tell me about yourself”)
A 4-step flow captures:
- goal
- experience
- biometrics
- constraints
Why? Because the engine needs typed inputs—not paragraphs.
Markdown coach responses
- Clean formatting (lists, emphasis)
- Safer rendering (user input stays plain)
Small detail, big UX upgrade.
Graceful degradation
No Gemini key?
- The system still runs
- Chat falls back to deterministic responses
Zero setup friction.
Infrastructure: deliberately boring
- Frontend: React + Vite + Tailwind
- Backend: Node + Express
- DB: SQLite (single file, backed up)
- Auth: Passport + sessions
- Deploy: Docker on **Fly.io
Why this stack?
Because complexity is the enemy of iteration—especially in v1.
A subtle but important detail
The app serves both:
- API routes (
/plan,/auth, etc.) - SPA routes (also
/planin the UI)
The server distinguishes based on
Accept: text/html.Without this, routing breaks in non-obvious ways.
What’s intentionally missing in the MVP
Not everything belongs in v1:
- Google Calendar sync
- advanced CTL/ATL analytics
- strength training templates
These are useful—but not critical.
Shipping them early adds surface area and support burden without strengthening the core loop.
The Real Product
EnduraCoach isn’t “AI coaching.”
It’s a system where:
- Rules ensure safety and consistency
- AI adds intelligence and usability
- The user stays in control
That combination matters.
Because in endurance training, credibility doesn’t come from elegant language—it comes from predictable progression and transparent decisions.
Bottom line
Most AI products ask: “What can the model do?”
This one asks:
“What should the model should not be allowed to do?”
That constraint is the product.
And it’s the reason it works.Rate this:
#AI #ironman #Sport #tools #webapp -
【地獄に堕ちるわよ】真実か？虚構か？伝説の占い師・細木数子のNETFLIX実写ドラマ初見ネタバレ感想 https://drama.io/884666/ #APEX #avengers #dcコミックス #drama #endgame #ironman #MARVEL #MCU #movie #SF #SPIDERMAN #spiederman #アイアンマン #アベンジャーズ #アメコミ #エンドゲーム #ゲーム #スカイウォーカーの夜明け #スターウォーズ #スパイダーマン #ドラマ #ドラマ紹介 #フェーズ４ #フェイズ４ #マーベル #モンスターワールド #モンハン #実況 #情報 #映画 #洋画 #考察 #解説
-
#QPosket Marvel: Iron Man – Battle Version (Type B) *Sealed* brought to you by the #PlastiqueBoutique https://plastiqueboutique.com/product/qposket-marvel-iron-man-battle-version-type-b-sealed/?utm_source=mastodon&utm_medium=social&utm_campaign=ReviveOldPost #MarvelToys #Marvel #IronManCollections #MarvelStatues #IronManCollection #MarvelCollectors #IronManToy #IronManFigures #MarvelCollection #MarvelFigure #IronMan #IronManCollector #IronManCollectors #MarvelCollections #MarvelToy #IronManFigure #IronManToys #MarvelStatue #MarvelFigures #MarvelCollector
-
#QPosket Marvel: Iron Man – Battle Version (Type B) *Sealed* brought to you by the #PlastiqueBoutique https://plastiqueboutique.com/product/qposket-marvel-iron-man-battle-version-type-b-sealed/?utm_source=mastodon&utm_medium=social&utm_campaign=ReviveOldPost #MarvelToys #Marvel #IronManCollections #MarvelStatues #IronManCollection #MarvelCollectors #IronManToy #IronManFigures #MarvelCollection #MarvelFigure #IronMan #IronManCollector #IronManCollectors #MarvelCollections #MarvelToy #IronManFigure #IronManToys #MarvelStatue #MarvelFigures #MarvelCollector
-
【ザ・スーパーマリオギャラクシー・ムービー】まさかの賛否両論を巻き起こしてるマリオ映画２作目の初見ネタバレ感想 https://drama.io/883531/ #APEX #avengers #dcコミックス #endgame #ironman #MARVEL #MCU #movie #SF #SPIDERMAN #spiederman #アイアンマン #アベンジャーズ #アメコミ #エンドゲーム #ゲーム #スカイウォーカーの夜明け #スターウォーズ #スパイダーマン #フェーズ４ #フェイズ４ #マーベル #モンスターワールド #モンハン #実況 #情報 #映画 #映画解説 #洋画 #考察 #解説
-
El Porsche 993 biturbo vestido de Iron Man
https://espirituracer.com/curiosidades/el-porsche-993-biturbo-vestido-de-iron-man/
#42A47 #Cabriolet #Curiosidades #Gasolina #Pelculas #Porsche #Reportajes #Restomod #Tuning #993 #CochesAlemanes #Endgame #IronMan #Porsche #Porsche911
#espirituRACER #coches #cars -
El Porsche 993 biturbo vestido de Iron Man
https://espirituracer.com/curiosidades/el-porsche-993-biturbo-vestido-de-iron-man/
#42A47 #Cabriolet #Curiosidades #Gasolina #Pelculas #Porsche #Reportajes #Restomod #Tuning #993 #CochesAlemanes #Endgame #IronMan #Porsche #Porsche911
#espirituRACER #coches #cars -
El Porsche 993 biturbo vestido de Iron Man
https://espirituracer.com/curiosidades/el-porsche-993-biturbo-vestido-de-iron-man/
#42A47 #Cabriolet #Curiosidades #Gasolina #Pelculas #Porsche #Reportajes #Restomod #Tuning #993 #CochesAlemanes #Endgame #IronMan #Porsche #Porsche911
#espirituRACER #coches #cars -
$12 pickup. 9 more regular Iron Man issues to go! #IronMan
-
https://www.europesays.com/fr/874894/ Marvel a montré la bande-annonce d’Avengers : Doomsday au CinemaCon #Avengers:Doomsday #Avengers5 #CaptainAmerica #Divertissement #Entertainment #FR #France #IronMan #Les4Fantastiques #Marvel #Thor
-
Peter Lohmann macht Dienst in Düsseldorf und ist jetzt als einer der erfolgreichsten Polizeisportler Deutschlands geehrt worden.#WDR #PeterLohmann #Polizist #Monheim #Polizeisportler #Ehrung #Triathlon #Ironman #Düsseldorf #Garath #NRW
Vom Streifenwagen zur Weltklasse: Peter Lohmann aus Monheim als Top-Polizeisportler geehrt -
Ironman EC Hamburg 2025
Bike Check-In | Video 2 of 2https://youtu.be/OWNZz5CROMg?is=t9g91ooOS759Ev4p
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg #nolympia #NOlympia_Hamburg@nolympia
@NOlympia_Hamburg
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace -
Ironman EC Hamburg 2025
Bike Check-In | Video 2 of 2https://youtu.be/OWNZz5CROMg?is=t9g91ooOS759Ev4p
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg #nolympia #NOlympia_Hamburg@nolympia
@NOlympia_Hamburg
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace -
Ironman EC Hamburg 2025
Bike Check-In | Video 2 of 2https://youtu.be/OWNZz5CROMg?is=t9g91ooOS759Ev4p
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg #nolympia #NOlympia_Hamburg@nolympia
@NOlympia_Hamburg
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace -
Ironman EC Hamburg 2025
Bike Check-In | Video 2 of 2https://youtu.be/OWNZz5CROMg?is=t9g91ooOS759Ev4p
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg #nolympia #NOlympia_Hamburg@nolympia
@NOlympia_Hamburg
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace -
Ironman EC Hamburg 2025
Bike Check-In | Video 1 of 2https://youtu.be/2bg4fExP9Pg?is=WiNctEiGVlj0xMhn
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg@ironman
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace
@NaturFreunde -
Ironman EC Hamburg 2025
Bike Check-In | Video 1 of 2https://youtu.be/2bg4fExP9Pg?is=WiNctEiGVlj0xMhn
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg@ironman
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace
@NaturFreunde -
Ironman EC Hamburg 2025
Bike Check-In | Video 1 of 2https://youtu.be/2bg4fExP9Pg?is=WiNctEiGVlj0xMhn
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg@ironman
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace
@NaturFreunde -
Ironman EC Hamburg 2025
Bike Check-In | Video 1 of 2https://youtu.be/2bg4fExP9Pg?is=WiNctEiGVlj0xMhn
#ironman #triathlon #hamburg
#adfc #ADFCHamburg #sternfahrt
#sternfahrt2026 #criticalmass
#criticalmasshamburg #visionzero
#verkehrswende #bike #fahrrad
#bicycle #fahrradbubble #TriTeamNN
#mobilohneautonordev #pruef #pruefhh
#VelorouteHamburg@ironman
@ADFC
@ADFC_Hamburg
@VelorouteHamburg
@FAHRRADkultur
@CriticalMass
@CriticalMassHamburg
@greenpeace
@NaturFreunde -
One year ago today I posted this miniature Iron Man photo I created using real figures, lighting and miniature sets.
#ironman #marvel #miniatures #tonystark #photography #photos #visualart #creativephotography #scifi #comics #actionfigurephotography #photographersunited #miniaturephotography
-
Movie TV Tech Geeks #MovieNews #RobertDowneyJr #IronMan #JonFavreau The Superhero Movie That Started a Billion-Dollar Franchise Proves It's Still One of the Best http://dlvr.it/TS0S5H
-
Iron Man through the trading card ages!
Which card is your favorite?
#TradingCardADay #IronMan #MU1 #MU2 #MU3 #MU4 #PaulRyan #JohnRomitaJr #JeffJohnson
-
Iron Man through the trading card ages!
Which card is your favorite?
#TradingCardADay #IronMan #MU1 #MU2 #MU3 #MU4 #PaulRyan #JohnRomitaJr #JeffJohnson
-
Iron Man through the trading card ages!
Which card is your favorite?
#TradingCardADay #IronMan #MU1 #MU2 #MU3 #MU4 #PaulRyan #JohnRomitaJr #JeffJohnson
-
016 - The Face Thief
While his first appearance is also the Face Thief's only appearance to date, this is a rare example of one of these new characters getting tied into an ongoing storyline.
Scans via @tradingcarddb
-
#OnThisDay Martin Luther King Jr. was assassinated (1968) at a motel in Memphis, Tennessee.
Microsoft was founded (1975) as a partnership between Bill Gates and Paul Allen.
Happy Birthday #IronMan Robert Downey Jr. (1965).
-
i’m afraid to inform you that i am now on #ironman tiktok
it’s entirely the algorithms fault
-
Here's two pieces of #artwork made by two students that studied under my friend Suphannee, they're done with oil paint on large canvases; both're available & affordable! Msg me if you're a #Dragonball or #IronMan fan & would like to support the arts ~
#art #arts #artist #artists #painting #paintings #anime #dragonball #dbz #dragonballz #ironman #marvel #marvelcomics #illustration #artforsale #artmarket #artfinder #artgallery #artgalleries #mastoart #artstodon #artistsonmastodon
-
Here's two pieces of #artwork made by two students that studied under my friend Suphannee, they're done with oil paint on large canvases; both're available & affordable! Msg me if you're a #Dragonball or #IronMan fan & would like to support the arts ~
#art #arts #artist #artists #painting #paintings #anime #dragonball #dbz #dragonballz #ironman #marvel #marvelcomics #illustration #artforsale #artmarket #artfinder #artgallery #artgalleries #mastoart #artstodon #artistsonmastodon
-
Here's two pieces of #artwork made by two students that studied under my friend Suphannee, they're done with oil paint on large canvases; both're available & affordable! Msg me if you're a #Dragonball or #IronMan fan & would like to support the arts ~
#art #arts #artist #artists #painting #paintings #anime #dragonball #dbz #dragonballz #ironman #marvel #marvelcomics #illustration #artforsale #artmarket #artfinder #artgallery #artgalleries #mastoart #artstodon #artistsonmastodon
-
Here's two pieces of #artwork made by two students that studied under my friend Suphannee, they're done with oil paint on large canvases; both're available & affordable! Msg me if you're a #Dragonball or #IronMan fan & would like to support the arts ~
#art #arts #artist #artists #painting #paintings #anime #dragonball #dbz #dragonballz #ironman #marvel #marvelcomics #illustration #artforsale #artmarket #artfinder #artgallery #artgalleries #mastoart #artstodon #artistsonmastodon
-
Don't Make Supergirl Angry - I love Supergirl since I was a kid and this is something I wanted to finish for a while but kept postponing. It is finally done. 4K Versions Of My Art Available For Supporters on P@TREON & SUBSTAR.
#Supergirl #KaraZorEl #DC #FanArt #HulkBuster #Ironman #Art #OC #MastoArt #FediArt
-
Don't Make Supergirl Angry - I love Supergirl since I was a kid and this is something I wanted to finish for a while but kept postponing. It is finally done. 4K Versions Of My Art Available For Supporters on P@TREON & SUBSTAR.
#Supergirl #KaraZorEl #DC #FanArt #HulkBuster #Ironman #Art #OC #MastoArt #FediArt
-
Don't Make Supergirl Angry - I love Supergirl since I was a kid and this is something I wanted to finish for a while but kept postponing. It is finally done. 4K Versions Of My Art Available For Supporters on P@TREON & SUBSTAR.
#Supergirl #KaraZorEl #DC #FanArt #HulkBuster #Ironman #Art #OC #MastoArt #FediArt
