AI Agents
posts (10)
- From Prompts to Agentic SDLC9/9
When Managed Agents are not enough: a platform for running agents
The ninth level shows the moment when an agent stops being only a Claude session and becomes a platform workload with IAM, networking, secrets, observability…
- From Prompts to Agentic SDLC8/9
Beyond Dynamic Workflows: when the workflow leaves Claude
The eighth level separates agent reasoning from durable orchestration: retries, webhooks, approvals, queues, long waits and workflow state outside Claude's…
- From Prompts to Agentic SDLC7/9
Claude beyond the terminal: three paths
The last upgrade in the core series shows three ways to move beyond the local terminal: remote control of a local session, cloud session and a Managed Agent…
- From Prompts to Agentic SDLC6/9
Dynamic Workflows: stop assuming the LLM will remember the whole workflow
The sixth upgrade moves the order of steps from model memory into an executable workflow that tracks stages, conditions, loops and verification.
- From Prompts to Agentic SDLC5/9
Subagents: stop putting all the work into one context
The fifth upgrade splits large work into separate contexts so implementation, review, testing and research do not mix inside one long session.
- From Prompts to Agentic SDLC4/9
Skills, Hooks and Permissions: write down the method, automate mechanics, reduce risk
The fourth upgrade separates three things: the way of working written as a skill, mechanical steps performed by hooks and risks constrained by permissions.
- From Prompts to Agentic SDLC3/9
Retrieval, RAG and MCP: stop being the API between Claude and the rest of the SDLC
The third upgrade is that Claude stops waiting for you to manually paste logs, issues, documentation or CI state, and starts getting the needed context itself.
- From Prompts to Agentic SDLC2/9
Context engineering: stop explaining your project to Claude every time
The second upgrade moves stable project rules from the conversation into the repository, documentation and tools, so Claude does not start every session from…
- From Prompts to Agentic SDLC1/9
From chat to agent: stop carrying code to AI
The first upgrade in working with an LLM is that the model stops being a consultant in another tab and starts executing the task directly in the repository.
- series · 9 parts
From Prompts to Agentic SDLC
This series moves from copying prompts between chat and IDE to agents that work in the repository, use context, tools, workflows, external orchestration and…