HealthKit + Celery on ECS, Part 3: Deploying Workers to Fargate
One Docker image, two ECS services, an SQS queue with IAM auth, and the Django settings crash that blocks every first Celery deploy.
Posts by Tag
- aws 7
- django 5
- ai 4
- agents 4
- celery 4
- strands 3
- ecs 3
- healthkit 3
- sqs 3
- python 2
- architecture 2
- llm 2
- flutter 2
- bedrock 1
- prompts 1
- safety 1
- guardrails 1
- hallucination 1
- data-integrity 1
- rag 1
- embeddings 1
- chromadb 1
- ollama 1
- mcp 1
- vector-search 1
- redis 1
- meta 1
- writing 1
- postgresql 1
- devops 1
- citations 1
- streaming 1
aws
HealthKit + Celery on ECS, Part 1: Why Background Processing Changes Everything
You can’t process Apple HealthKit data inline. Here’s why we needed Celery with SQS, how Redis fits in separately for caching, and the architecture that emer...
Celery on ECS: Separate Container Architecture
A visual deep-dive into running Celery workers as separate ECS containers — broker topology, task lifecycle, concurrency models, and the Beat scheduler gotcha.
Building an AI Health Agent with AWS Strands - Part 4: Anti-Hallucination
Part 4 of building the AI assistant. This covers the most critical issue in health AI: preventing the model from making up data that doesn’t exist.
Building an AI Health Agent with AWS Strands - Part 3: Prompts & Guardrails
Part 3 of the series on building a women’s health AI assistant. This covers the system prompts, safety guardrails, and behavior control that make an AI agent...
Building an AI Health Agent with AWS Strands - Part 1: Architecture
This is the first in a series documenting how I built a women’s health AI assistant using AWS Strands SDK, Bedrock, and Django. The system handles personal h...
AWS Strands Agents: User-Scoped Tools Without Breaking @tool Decorators
If you’re building multi-user AI agents with AWS Strands SDK, you’ll quickly hit a common problem: how do you bind tools to a specific user without passing u...
django
Building a Markdown-First Citation Pipeline for an AI Health Agent
How I replaced inline URL citations with a token-based reference system that separates machine semantics from user-visible text — and why the old approach wa...
HealthKit + Celery on ECS, Part 3: Deploying Workers to Fargate
One Docker image, two ECS services, an SQS queue with IAM auth, and the Django settings crash that blocks every first Celery deploy.
HealthKit + Celery on ECS, Part 2: The Sync Pipeline
A chunk-based import pipeline with SQS, dispatcher tasks that chain through the queue, fingerprint deduplication, and why we track batch state in PostgreSQL ...
HealthKit + Celery on ECS, Part 1: Why Background Processing Changes Everything
You can’t process Apple HealthKit data inline. Here’s why we needed Celery with SQS, how Redis fits in separately for caching, and the architecture that emer...
Celery on ECS: Separate Container Architecture
A visual deep-dive into running Celery workers as separate ECS containers — broker topology, task lifecycle, concurrency models, and the Beat scheduler gotcha.
ai
Building an AI Health Agent with AWS Strands - Part 4: Anti-Hallucination
Part 4 of building the AI assistant. This covers the most critical issue in health AI: preventing the model from making up data that doesn’t exist.
Building an AI Health Agent with AWS Strands - Part 3: Prompts & Guardrails
Part 3 of the series on building a women’s health AI assistant. This covers the system prompts, safety guardrails, and behavior control that make an AI agent...
Building an AI Health Agent with AWS Strands - Part 1: Architecture
This is the first in a series documenting how I built a women’s health AI assistant using AWS Strands SDK, Bedrock, and Django. The system handles personal h...
AWS Strands Agents: User-Scoped Tools Without Breaking @tool Decorators
If you’re building multi-user AI agents with AWS Strands SDK, you’ll quickly hit a common problem: how do you bind tools to a specific user without passing u...
agents
Building an AI Health Agent with AWS Strands - Part 4: Anti-Hallucination
Part 4 of building the AI assistant. This covers the most critical issue in health AI: preventing the model from making up data that doesn’t exist.
Building an AI Health Agent with AWS Strands - Part 3: Prompts & Guardrails
Part 3 of the series on building a women’s health AI assistant. This covers the system prompts, safety guardrails, and behavior control that make an AI agent...
Building an AI Health Agent with AWS Strands - Part 1: Architecture
This is the first in a series documenting how I built a women’s health AI assistant using AWS Strands SDK, Bedrock, and Django. The system handles personal h...
AWS Strands Agents: User-Scoped Tools Without Breaking @tool Decorators
If you’re building multi-user AI agents with AWS Strands SDK, you’ll quickly hit a common problem: how do you bind tools to a specific user without passing u...
celery
HealthKit + Celery on ECS, Part 3: Deploying Workers to Fargate
One Docker image, two ECS services, an SQS queue with IAM auth, and the Django settings crash that blocks every first Celery deploy.
HealthKit + Celery on ECS, Part 2: The Sync Pipeline
A chunk-based import pipeline with SQS, dispatcher tasks that chain through the queue, fingerprint deduplication, and why we track batch state in PostgreSQL ...
HealthKit + Celery on ECS, Part 1: Why Background Processing Changes Everything
You can’t process Apple HealthKit data inline. Here’s why we needed Celery with SQS, how Redis fits in separately for caching, and the architecture that emer...
Celery on ECS: Separate Container Architecture
A visual deep-dive into running Celery workers as separate ECS containers — broker topology, task lifecycle, concurrency models, and the Beat scheduler gotcha.
strands
Building a Markdown-First Citation Pipeline for an AI Health Agent
How I replaced inline URL citations with a token-based reference system that separates machine semantics from user-visible text — and why the old approach wa...
Building an AI Health Agent with AWS Strands - Part 1: Architecture
This is the first in a series documenting how I built a women’s health AI assistant using AWS Strands SDK, Bedrock, and Django. The system handles personal h...
AWS Strands Agents: User-Scoped Tools Without Breaking @tool Decorators
If you’re building multi-user AI agents with AWS Strands SDK, you’ll quickly hit a common problem: how do you bind tools to a specific user without passing u...
ecs
HealthKit + Celery on ECS, Part 3: Deploying Workers to Fargate
One Docker image, two ECS services, an SQS queue with IAM auth, and the Django settings crash that blocks every first Celery deploy.
HealthKit + Celery on ECS, Part 1: Why Background Processing Changes Everything
You can’t process Apple HealthKit data inline. Here’s why we needed Celery with SQS, how Redis fits in separately for caching, and the architecture that emer...
Celery on ECS: Separate Container Architecture
A visual deep-dive into running Celery workers as separate ECS containers — broker topology, task lifecycle, concurrency models, and the Beat scheduler gotcha.
healthkit
HealthKit + Celery on ECS, Part 3: Deploying Workers to Fargate
One Docker image, two ECS services, an SQS queue with IAM auth, and the Django settings crash that blocks every first Celery deploy.
HealthKit + Celery on ECS, Part 2: The Sync Pipeline
A chunk-based import pipeline with SQS, dispatcher tasks that chain through the queue, fingerprint deduplication, and why we track batch state in PostgreSQL ...
HealthKit + Celery on ECS, Part 1: Why Background Processing Changes Everything
You can’t process Apple HealthKit data inline. Here’s why we needed Celery with SQS, how Redis fits in separately for caching, and the architecture that emer...
sqs
HealthKit + Celery on ECS, Part 3: Deploying Workers to Fargate
One Docker image, two ECS services, an SQS queue with IAM auth, and the Django settings crash that blocks every first Celery deploy.
HealthKit + Celery on ECS, Part 2: The Sync Pipeline
A chunk-based import pipeline with SQS, dispatcher tasks that chain through the queue, fingerprint deduplication, and why we track batch state in PostgreSQL ...
HealthKit + Celery on ECS, Part 1: Why Background Processing Changes Everything
You can’t process Apple HealthKit data inline. Here’s why we needed Celery with SQS, how Redis fits in separately for caching, and the architecture that emer...
python
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
AWS Strands Agents: User-Scoped Tools Without Breaking @tool Decorators
If you’re building multi-user AI agents with AWS Strands SDK, you’ll quickly hit a common problem: how do you bind tools to a specific user without passing u...
architecture
Building a Markdown-First Citation Pipeline for an AI Health Agent
How I replaced inline URL citations with a token-based reference system that separates machine semantics from user-visible text — and why the old approach wa...
Building an AI Health Agent with AWS Strands - Part 1: Architecture
This is the first in a series documenting how I built a women’s health AI assistant using AWS Strands SDK, Bedrock, and Django. The system handles personal h...
llm
Building a Markdown-First Citation Pipeline for an AI Health Agent
How I replaced inline URL citations with a token-based reference system that separates machine semantics from user-visible text — and why the old approach wa...
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
flutter
HealthKit + Celery on ECS, Part 2: The Sync Pipeline
A chunk-based import pipeline with SQS, dispatcher tasks that chain through the queue, fingerprint deduplication, and why we track batch state in PostgreSQL ...
HealthKit + Celery on ECS, Part 1: Why Background Processing Changes Everything
You can’t process Apple HealthKit data inline. Here’s why we needed Celery with SQS, how Redis fits in separately for caching, and the architecture that emer...
bedrock
Building an AI Health Agent with AWS Strands - Part 1: Architecture
This is the first in a series documenting how I built a women’s health AI assistant using AWS Strands SDK, Bedrock, and Django. The system handles personal h...
prompts
Building an AI Health Agent with AWS Strands - Part 3: Prompts & Guardrails
Part 3 of the series on building a women’s health AI assistant. This covers the system prompts, safety guardrails, and behavior control that make an AI agent...
safety
Building an AI Health Agent with AWS Strands - Part 3: Prompts & Guardrails
Part 3 of the series on building a women’s health AI assistant. This covers the system prompts, safety guardrails, and behavior control that make an AI agent...
guardrails
Building an AI Health Agent with AWS Strands - Part 3: Prompts & Guardrails
Part 3 of the series on building a women’s health AI assistant. This covers the system prompts, safety guardrails, and behavior control that make an AI agent...
hallucination
Building an AI Health Agent with AWS Strands - Part 4: Anti-Hallucination
Part 4 of building the AI assistant. This covers the most critical issue in health AI: preventing the model from making up data that doesn’t exist.
data-integrity
Building an AI Health Agent with AWS Strands - Part 4: Anti-Hallucination
Part 4 of building the AI assistant. This covers the most critical issue in health AI: preventing the model from making up data that doesn’t exist.
rag
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
embeddings
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
chromadb
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
ollama
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
mcp
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
vector-search
How I Built a Local RAG System for My Obsidian Notes
I have 268 markdown files in my Obsidian vault – internal docs, architecture decisions, API specs, meeting notes. Searching them with Obsidian’s built-in sea...
redis
Celery on ECS: Separate Container Architecture
A visual deep-dive into running Celery workers as separate ECS containers — broker topology, task lifecycle, concurrency models, and the Beat scheduler gotcha.
meta
Hello World — Why I’m Starting This Blog
After 14 years of building software, I’m finally writing about it.
writing
Hello World — Why I’m Starting This Blog
After 14 years of building software, I’m finally writing about it.
postgresql
HealthKit + Celery on ECS, Part 2: The Sync Pipeline
A chunk-based import pipeline with SQS, dispatcher tasks that chain through the queue, fingerprint deduplication, and why we track batch state in PostgreSQL ...
devops
HealthKit + Celery on ECS, Part 3: Deploying Workers to Fargate
One Docker image, two ECS services, an SQS queue with IAM auth, and the Django settings crash that blocks every first Celery deploy.
citations
Building a Markdown-First Citation Pipeline for an AI Health Agent
How I replaced inline URL citations with a token-based reference system that separates machine semantics from user-visible text — and why the old approach wa...
streaming
Building a Markdown-First Citation Pipeline for an AI Health Agent
How I replaced inline URL citations with a token-based reference system that separates machine semantics from user-visible text — and why the old approach wa...