Topic
Constraint Specification
5 episodes
-
The MCP debate has a context problem
Ava opens skeptical on the 'MCP context problem' framing—questioning whether the article's governance tension is a real bottleneck or a vendor-invented problem. Vince steelmans: for teams actually shipping agentic workflows, the boundary between what an agent can access and what it shouldn't is genuinely hard to specify upstream, and MCP's protocol-layer answer to that is a real unlock. They argue through whether the problem is *real* (both land yes) versus *urgent* (Ava: solved at runtime anyway; Vince: solved earlier costs less). Honest verdict: MCP's governance layer is architecturally sound but the article oversells urgency—the real win is that you CAN specify it at protocol time now, not that you MUST.
-
Long Horizon Terminal Bench: Testing the Limits of Agents on Long Horizon Terminal Tasks with Dense Reward Based Grading
Laura and Harper dig into Long-Horizon-Terminal-Bench, a new benchmark exposing the gap between short-task agent demos and real multi-hour workflows. They break down the dense-reward grading system, the staggering token costs (9.9M per task), and why current models are failing at sustained execution despite high step-level competence.
-
How I Built an Agentic Research System
Onyx and Echo unpack Hugo Santana’s ‘agentic research system’ for Applied’s living map of AI deployments. They dig into the five agents (Scout, Extractor, Enrichment, Translator, QA, Match Maker), call out what works (simple orchestration via a shared living map and logs), and where it over-indexes (taxonomy drift, closed-loop feedback still manual). They then map the pattern to other domains—competitor research, policy tracking—and debate who should actually care (practitioners who need a reliable, repeatable funnel of fresh signals). The close lands on whether this architecture is a general-purpose engine or a bespoke project that still needs a human at the taxonomy helm.
-
Don't rewrite your CLI for agents Microsoft for Developers
Microsoft's data shows agents handle complex CLIs with traditional args better than JSON payloads: higher correctness for smaller models, 4-11x lower cost, and fewer shell-escaping failures. The constraint of args compensates for model gaps.
-
Harness engineering for coding agent users
Vince and Ava discuss Birgitta Böckeler's Martin Fowler article on harness engineering for coding agents — the feedforward/feedback model, computational vs inferential controls, and why the behaviour harness category remains unsolved.