shamirai.ai

a live map of what I'm learning, what I'm building, and what I finished.

20 nodes
0 reported · 2 executing · 18 learning

drag to pan · scroll to zoom · click a node

shamirai.ai

learn, execute, report. mostly for me.

Building shamirai.ai executing runtime & infra This site. A map of what I am learning rather than a list of what I have finished. in progress Loop engineering executing harness & loops Designing the iteration itself: when to continue, retry, escalate, compact, or stop. Most agent failures are loop failures, not model failures. in progress

queued, not started

Agent execution graphs learning harness & loops Expressing agent control flow as an explicit DAG or state machine instead of a free-running loop. Buys inspectability and resumability, costs flexibility. Agent trajectory eval learning evaluation Scoring the path an agent took rather than just its final answer: redundant calls, recovery from errors, dead ends. Final-answer accuracy hides all of it. Context compaction learning agent architectures What a long-running agent throws away when the window fills, and how it decides. Summarise, score-and-drop, or offload to storage. Chunking strategies learning retrieval How you split documents before embedding them: size, overlap, and whether to respect structure. The variable that quietly decides retrieval quality. Durable Objects as agent state learning runtime & infra Cloudflare's single-instance stateful objects as a home for one agent's memory: alive between requests, strongly consistent, one per session. Graph RAG learning retrieval Retrieving over a graph of entities and relationships rather than flat chunks, so questions needing two or three hops stop failing. Harness engineering learning harness & loops Designing everything around the model: tool surface, context assembly, permissions, feedback. The scaffolding that decides whether a capable model is actually useful. Hybrid search: BM25 + dense learning retrieval Combining keyword search (BM25) with vector search, and the real problem: how to fuse two ranked lists that disagree. Knowledge graphs as memory learning agent architectures A graph the agent writes to as it goes, rather than a static index it only reads. Memory with explicit relationships instead of a pile of embeddings. LLM-as-judge learning evaluation Using a model to grade model output. Cheap and scalable, and quietly vulnerable to position bias and self-preference. MCP server authoring learning protocol & tooling Building a Model Context Protocol server so an agent can use your own data and actions as first-class tools rather than pasted context. Prompt regression suites learning evaluation Test suites for prompts, so a change that fixes one case does not silently break twelve others you were not looking at. Multi-agent orchestration learning agent architectures Splitting work across specialised agents (planner, worker, critic), and whether the quality gain survives the cost of every handoff. ReAct loops learning agent architectures The reason / act / observe cycle underneath most agents. The baseline every fancier architecture gets measured against. Streaming and backpressure learning runtime & infra Streaming tokens when the consumer is slower than the producer, and what to actually do when the buffer fills. Tool descriptions as the API learning protocol & tooling The claim that a tool's prose description, not its type signature, is the real interface the model programs against, and that writing it is design work. Tool-use error recovery learning agent architectures What you hand back when a tool call fails: the raw error, a translated message, or a suggested fix. The choice changes recovery rates a lot. Workers AI at the edge learning runtime & infra Running inference and embeddings inside a Cloudflare Worker: no origin server, no API key, no cold-start infrastructure to manage.