Claude - FinanceAI by Sergio Jardon

Sign in Subscribe

Claude

A collection of 9 posts

Context Rot: Why Stuffing More Into Your Prompt Can Make Things Worse

Context Rot: Why Stuffing More Into Your Prompt Can Make Things Worse

It's tempting to treat a large context window as a dumping ground, paste in the whole document, the whole chat history, the whole knowledge base, and let the model sort it out. Research from Chroma (July 2025) shows why that instinct backfires. Testing 18 leading LLMs, including GPT-

Cut Your Agent's Token Bill by 98% With Code Execution

Cut Your Agent's Token Bill by 98% With Code Execution

Here's a pattern to cut down your bill significantly and it's changing how agent builders use the Model Context Protocol (MCP): stop calling tools directly, and let the agent write code instead. How this works? A typical agent loads every connected MCP server's full

Stop Routing Data Through Your LLM

Stop Routing Data Through Your LLM

Here's a pattern worth stealing if you're building agents that connect to more than a handful of tools: code execution with MCP. The default way most agent frameworks use the Model Context Protocol is to load every connected tool's full definition into context up

Your AI agent doesn't need the whole database

Your AI agent doesn't need the whole database

Here's a mistake I see when people build their first AI agent: they treat the context window like a bucket to fill. Got a customer database? Paste it in. A log file? Paste it in. In practice this backfires, the model gets buried in irrelevant rows, burns tokens

Beat Context Rot: Give Your AI Agent a Memory

Beat Context Rot: Give Your AI Agent a Memory

Beat Context Rot: Give Your AI Agent a Memory

Agent #005 The ops monitor

Agent #005 The ops monitor

The final agent in the AI Dev Squad watches your CI/CD pipelines around the clock. But the most important part of this post isn't the agent, it's the safety architecture that makes all five agents trustworthy in production.

Agents #003 and #004: Doc Writer and QA Agent. Documentation and Tests on Autopilot

Agents #003 and #004: Doc Writer and QA Agent. Documentation and Tests on Autopilot

Documentation is always out of date. Tests are always written last, if at all. Two agents fix both problems simultaneously , one updates your README, CHANGELOG, and API docs on every merge; the other generates test scaffolding the moment a Jira ticket moves to development.

Agent #002 - The Code Reviewer

Agent #002 - The Code Reviewer

Every pull request your team opens deserves a first review. Here is how to build an agent that reads every PR, detects bugs and security issues, posts structured feedback on Github and notifies. Before your first coffee

Agent 001: The Scrum Master

Agent 001: The Scrum Master

Your daily standup takes 30 minutes and produces a 90-second summary that nobody reads. Here's how to build an AI agent that reads your entire Jira sprint every morning, detects blockers automatically, and posts a structured report to Slack, before you even blink your eyes.