Applied Intelligenceby Arseny Gorokh · @agorokh
applied AI research · independent
in this issue ·ai-09 ·applied research note ·4 jul 2026 ·12 min read

"It's done." The most expensive tokens an agent produces.an independent test of completion gates for coding agents, and what an enterprise agent program should copy from it.

Enterprise agent programs have spent three years excited about building agents and almost no time on the question that decides their value: what exactly is the definition of done, and who checks it? A new paper from Purdue answers it structurally, completion as a validated workspace state, and this note replicates it independently with a different agent family on the authors' released harness, unmodified. The gate passed, refused four genuinely wrong results on the way, and the note separates what is science from the five practices an enterprise program can adopt now.

Read the note  ›
2
agent families have now passed the same completion gate: the authors' own, and this replication's, which met the harness cold. The discipline lives in the workspace, not the model.
4
attempts the validators refused mid-run, across three targets; every refusal was a real method error that an unchecked workflow would have shipped as done.
11 of 11
planned replication targets reached MATCHED with all four validators green; what "planned" hides is the first of the two limits the note demonstrates.
half
of claims, at worst, received the same acceptance-rule type across the authors' own repeated runs. The judgment gap the gate does not close, computed from their released data.

the archive

every note carries one folio. the magnitudes are corpus-specific; the structural claims are what transfer.
ai-094 jul 2026agent verification "It's done." The most expensive tokens an agent produces.Agent completion as a validated workspace state, independently replicated with a different agent family on the authors' released harness, unmodified; four refusals on the way, every one a real method error, and the science explicitly separated from the five practices an enterprise agent program can adopt now. 12 min ai-082 jul 2026engineering memory The meeting forgets. The pull request remembers.Conventional engineering culture discards the reasoning behind its decisions at a measured, well-documented rate; an agent-first workflow preserves the chain as queryable artifacts and enforces the reading. The measured half, the hypothesis half, and the falsifiers. 11 min ai-0730 jun 2026model routing Three open models drove Claude Code through its governance gatesGLM 5.2, Qwen 3.7 Plus, and Kimi K2.7 Code solved an identical fix perfectly, so they separate only under governance friction; a scan of 627 sessions found zero faked-compliance and exonerated the model the first read accused. 14 min ai-0613 jun 2026agent data MCP harvesting: trustworthy data when your agent has a connector, not an APIAn agent that can only reach a system through a flaky MCP connector treats its output as evidence to check, not a value to trust; an entailment gate caught 98 percent of unsupported claims where a similarity gate caught 27. 18 min ai-055 jun 2026agent memory A memory-and-policy layer above the model: the build-versus-buy caseA gateway routes a prompt but does not know the repository, policy, or budget; own the in-path layer that governs memory, policy, and cost while the model stays swappable, and prove it ports across providers. 12 min ai-0419 may 2026memory substrate Choosing the memory substrate for enterprise agents: LightRAG, Graphiti, and the weighting that decidesTwo purpose-built substrates and a filesystem baseline against a five-criterion adoption bar on an SDLC corpus; production weighting separates them by 36 points where uniform weighting calls it a tie, and the entity graph fabricated four times where the chunk-text retriever never did. 14 min ai-0315 may 2026agent telemetry Claude Code through DIAL: eight models, 192 runs, and metering every requestA POC connecting Claude Code to DIAL across eight models; the cheapest that passes everything is open-source, and the routing adapter meters every request for a per-project view of AI-coding cost. 17 min ai-0214 may 2026open models Which models can run Claude Code through DIAL? Five upstreams, and the costThree Anthropic tiers and two open Qwen coders through one gateway; an open 480B passed every task at $0.101 each, the cheapest of the field, and capability tracks scale, not vendor. 16 min ai-0128 apr 2026ingest model Picking the extraction LLM for knowledge-graph ingestion: breadth beats densityEleven models measured as the entity-extraction LLM for a knowledge-graph RAG system; Gemini 2.5 Flash cleared every retrieval cell at roughly three percent of the strongest commercial model's ingest cost, because breadth of extraction beats density of relations. 16 min

An applied-AI reading style, for work that has to survive diligence.

Applied Intelligence is an independent practitioner publication. Each note takes one piece of real engineering, an agent, an adapter, a gateway, a gate, and reports what held and what did not, with the magnitudes kept honest and the structural claims stated so another team can re-derive them.

The register is deliberate: calm on the surface, hard engineering underneath. A finding leads; the evidence follows; the method and the limits sit where a reader can check them. The companion repositories are artefacts, one click away, never decoration: sdlc-dial-adapter and agentic-memory-mcp.

Written by Arseny Gorokh. The notes draw on real systems and name the public platforms they study; all client-specific material is excluded, and the notes are not official publications of any employer.

the publication
notes9
latestai-09
registerapplied AI research
set inNewsreader
elsewhere
An Applied Intelligence publication · independent · 2026 by Arseny Gorokh Set in Newsreader & Spline Sans Mono · the Applied Intelligence reading style