Deep-dive guides on AI agents, agent orchestration, MCP, and developer tooling.
15 posts found
Agent traces have a runtime-decided shape, token-based cost, and cross-process tool hops that conventional APM was never built for — here is what OpenTelemetry's gen_ai.* conventions actually pin down, and where tracing an agent loop still breaks in production.
SWE-bench is the most credible agentic coding benchmark available, but its leaderboard number answers a narrower question than most headlines imply — here is exactly what it does and does not test.
AlphaFold's Nobel Prize and GNoME's 2.2 million materials both got real headlines — but the honest story is about candidate generation, not discovery, and the gap between those two claims is where the hype lives.
A side-by-side look at pricing, context windows, and tiering across the three frontier model families as of August 2026 — and why the spec sheet undersells how differently they actually behave in agent loops.
Klarna's AI assistant did the work of 700 agents, then the company started rehiring humans. The real story is that support AI succeeds in narrow, policy-bounded tiers and breaks hard the moment it touches judgment calls and liability.
In agent systems, instructions live across four surfaces — system prompt, tool schemas, tool results, and few-shot text — not one. Most prompt debugging still only looks at the first.
Long-running agents rarely fail because they run out of context window — they fail because nobody designed what happens to attention quality once the transcript outgrows what the model can usefully weigh. Here is how tiered compaction, tool-output pruning, and sub-agent isolation actually work.
RAG is not one architecture — it is three structurally different systems with different costs and failure modes. Here is what actually changes between naive, agentic, and graph-based retrieval, and how to pick without over-building.
The three dominant multi-agent orchestration topologies each fail in a different, predictable way once you move past the demo — here is how to pick one based on where your task actually breaks, not which pattern sounds more sophisticated.
Most agent security advice targets prompt injection at the wrong layer. The real fix is architectural: separate untrusted tool output from privileged context, scope tool capabilities narrowly, and gate side-effecting actions behind confirmation.
Benchmark leaderboards measure task completion under lab conditions, not the compounding step failures that sink agents in production. Here is the math, and a blueprint for an eval harness that actually predicts reliability.
Vector similarity search answers what text is topically related — but long-running agents need to know what is true right now. Conflating the two is why agents keep resurrecting overturned decisions.