EXHIBIT 01 · ENTRY AUDIT
Entry audit
An inventory of your AI surface — what tooling already exists, what's shadow IT, where knowledge quietly drifts between systems. This document is yours to act on, with or without us.
See how we run this
Verification-first Claude Code consulting
We don't guess.
We don't guess.
We verify.
AI Architect is a consulting practice that activates verified AI agents inside your infrastructure — on the same stack we ship in production: 98.20% recall (MRR 0.9166) on LongMemEval, 5 fused retrieval signals, zero LLM-judges-LLM. Every output is traceable, every claim is checked — by deterministic algorithms, not by another model's opinion.
The zetetic standard
Four principles. No exceptions.
Zetetic comes from zētēsis — Greek for inquiry. Truth is something you investigate, not something you assume. Everything we ship enforces this.
i. PROVENANCE
Every claim has a source.
If an agent states a fact, that fact ties back to a memory, a file, a commit, or a citation. No assertion lives without a trail.
ii. ALGORITHM > OPINION
Zero LLM-judges-LLM.
Verification is deterministic: graph analysis, semantic checks, atomic claim decomposition. We don't ask one model whether another model is right.
iii. MEMORY THAT LEARNS
Compounding context.
Cortex applies neuroscience — spreading activation, consolidation cycles, microglial pruning — so agents remember what worked, not just what happened.
iv. AUDITABLE
Built for regulated work.
Every PRD, PR, decision and reasoning step is logged and reviewable. Designed against the same bar as financial-systems software.
Verification, in the open
Watch an agent prove its work.
This is the actual verification report from a generated PRD. 64 atomic claims, decomposed and checked against six independent algorithms. The full audit trail lives next to the deliverable — not buried in a log file.
Tooling of the engagement
The instruments we bring to every engagement. Not the offer — the toolkit.
These aren't what you're buying — they're what we run during an engagement. Cortex remembers, Zetetic reasons, Codebase maps, AI Architect Spec adjudicates. Every one ships open source, so you can inspect exactly what touches your systems.
// memory
v4.14.3
Cortex
Persistent memory for Claude Code.
recall@10cortex@cortex-plugins
98.20%
LongMemEval
LongMemEval
// agents
v2.29.0
Zetetic Agents
Reasoning patterns. One epistemic standard.
reasoning.chainzetetic-team-subagents
119agents
97 + 22 specialists
97 + 22 specialists
// pipeline
v0.7.0
AI Architect Codebase
Read-only codebase intelligence.
scan.completeai-architect-mcp-codebase
24MCP tools
10 stages
10 stages
// spec
v0.6.0
AI Architect Spec
Stateless reducer. Feature description → verified PRD.
spec.compileai-architect-mcp-spec
17MCP tools
10 pipeline steps
10 pipeline steps
// visualization
v2.6.3
cortex-viz
Read-only visualization for Cortex's memory store.
render.completecortex-viz
6reading
angles
angles
// context budget
v1.4.3
session-optimizer
Enforced context budget for long Claude Code sessions.
checkpoint.armedsession-optimizer
2status bar
lines
lines
Read-only companions
They never write. They only show you what's there.
Two small, focused MCPs that sit on top of Cortex and your session — neither touches the memory store, they read it.
// visualization
cortex-viz
Six read-only reading angles over Cortex's store: Graph, an anatomical 3D brain view (MNI152-registered cortical mesh), Trace, Knowledge, Wiki, Board. Reads PostgreSQL read-only; renders, never remembers.
v2.6.3 · cdeust/cortex-viz // context budgetsession-optimizer
A visible, enforced context budget for long Claude Code sessions: a two-line status bar tied to real per-model checkpoint thresholds, plus a Stop hook that performs the checkpoint automatically before a session grows past the point where it costs more and reasons worse.
v1.4.3 · cdeust/session-optimizer
Two ways to start
Hire us to build it. Or build it yourself with our tools.
Every component is open source, MIT-licensed, and shipping in production. The choice is whether you want the system handed to you — or the keys to do it yourself.
EXHIBIT PRIMARY ENGAGEMENT
For teams & founders
We build the
agent with you.
For operators who know AI should help — but don't want to spend six months stitching tutorials together. We design and ship the agent against your real infrastructure. Same engineering bar as the financial systems we build by day.
- Discovery — find the one workflow worth automating
- Built against your CRM, data, internal tools — not a sandbox
- Verification baked in: every action is auditable
- Hand-over with documentation & 30 days of post-launch support
For developers
Grab the templates.
Grab the templates.
Ship faster.
If you build with AI yourself, use the same components we use in production. Cortex, Zetetic Agents, AI Architect Codebase, and AI Architect Spec — each an independent plugin, fully documented, MIT-licensed, no telemetry, no lock-in.
- Cortex — persistent memory, 36 neuroscience mechanisms
- Zetetic Agents — 119 reasoning patterns, one epistemic standard
- AI Architect Codebase — read-only codebase intelligence (Rust MCP, 10 languages)
- AI Architect Spec — 17 MCP tools, 10-step pipeline + multi-judge verification, specialized panels by claim type
How engagements run
From entry audit to rollout. Four exhibits.
Every engagement runs the same sequence — no slide decks, no "AI transformation" theater. Each stage produces a visible, dated artifact before we ask for the next commitment.
EXHIBIT 02 · ACTIVATION
Claude Code activation
Scope, deploy, configure, run — the same activation sequence every time. We wire Claude Code into your real repos, your real data, your real review process.
See how we run thisEXHIBIT 03 · PAID PILOT
Paid pilot
A scoped, paid pilot against one real workflow, with deliverables visible as they ship — no black box. You watch the agent work before committing to anything past the pilot.
See how we run thisEXHIBIT 04 · ROLLOUT
Rollout
Two ways to run it in production: the local edition, on your own infrastructure with no dependency on us, or Claude Enterprise, managed with org-wide memory and governance. Either way, you own what ships.
See how we run this
founder
About
I ship critical systems by day. I research how agents should think by night.
By day I build software in financial infrastructure, where "mostly works" never ships. Every system has to be tested, verified, auditable. Or it doesn't go live.
By night I apply that same bar to AI. I started AI Architect because I kept seeing the same anti-pattern: teams treating agents like demos, stacking prompts on prompts, asking another LLM whether the first one got it right, and wondering why nothing held up in production.
The work here is zetetic — every claim is investigated, never assumed. The tools are open source because the frontier should be shared. The consulting exists because some teams need the system built with them, not handed a repo and a prayer.
"An agent without memory isn't intelligent. An agent without verification isn't trustworthy. I'm only interested in building both."
2 papers in review · seeking arXiv endorsement · cs.IR
The papers behind the numbers.
The papers behind the numbers.
Read them. Help us publish.
arXiv requires an endorser in cs.IR for first-time authors. Two preprints are ready — a third on HALO retrieval is in progress. Both drafts below are the work behind the LongMemEval, LoCoMo, and BEAM results on this page. If you've published in cs.IR and find them useful, a single endorsement gets each to the open scientific record.
Stage-Aware Context Assembly for Long-Context Memory Retrieval
+33.4%MRR · vs BEAM oracle
0.471MRR · BEAM-10M
8 / 10memory abilities improved
A structured context-assembly architecture that recovers the geometric degradation of dense vector retrieval at the 10M-token scale. Two primitives: a priority-budgeted prompt decomposer with domain-aware condensers, and a two-phase stage-aware assembler with submodular coverage selection, Personalized PageRank entity-graph traversal, and schema-structured summary fallback.
On BEAM-10M, the assembler reaches 0.471 MRR — +33.4% over the flat baseline, with 8 of 10 memory abilities improving. Originally designed in September 2025 for Apple Intelligence's 4,096-token window — one month before the BEAM benchmark itself was published.
Looking for an endorser
arXiv's policy requires an existing cs.IR author to endorse first-time submitters. If you've published in cs.IR and you find this useful, a single endorsement is enough — the rest is automated. Reach out below or open an issue on the repo.
Thermodynamic Memory vs. Flat-Importance Stores: Why Long-Term Retrieval Collapses Without Decay
98.4%R@10 · LongMemEval
94.2%R@10 · LoCoMo
0.591Overall · BEAM
External memory for LLMs is dominated by flat-importance stores — vector indexes, BM25 corpora, long-context buffers — in which every item carries the same long-term retrieval prior. This design is asymptotically broken: as the corpus grows, top-k retrieval degenerates into near-arbitrary tie-breaking.
This paper formalises the collapse and describes Cortex, a memory architecture that maintains a non-flat priority distribution across N by coupling four mechanisms: continuously decaying heat (Ebbinghaus), a hierarchical predictive-coding write gate (Friston), consolidation cascades (Kandel, McClelland), and WRRF fusion with heat as tie-breaker. The figures above are this paper's own measurement run (May 2026); the live shipped-code numbers on this page (98.20% / 91.35%) come from the v4.14.3 release-tree verification and supersede these as the current benchmark of record.
Looking for an endorser
Same endorsement ask as paper #1 — both submissions are independent. If you can endorse only one, this one establishes the underlying principle the other builds on.
Forthcoming — preprint #3: HALO retrieval. Drafting in progress; will join the same endorsement queue once complete.
Standing on shoulders
The science behind the system.
Cortex draws from a 97-paper bibliography across neuroscience, memory research and AI evaluation. A few of the load-bearing ones:
Wegner, 1987Transactive Memory: A Contemporary Analysis of the Group Mind
Hebb, 1949The Organization of Behavior — synaptic plasticity foundations
Friston, 2005A theory of cortical responses — predictive-coding write gate
Bi & Poo, 2001STDP — Spike-Timing-Dependent Plasticity
Wu et al., ICLR 2025LongMemEval — benchmark for chat assistants on sustained memory
Maharana et al., ACL 2024LoCoMo — Long-Conversation Memory benchmark
Schaffer et al., 2018Microglial pruning & memory selectivity
Tononi & Cirelli, 2014Synaptic Homeostasis Hypothesis (sleep)
+ 89 moreFull bibliography in the Cortex repo (docs/papers/bibliography.md)
Common questions
Before you
Before you
book a call.
Yes. Most non-tech clients bring a business problem and access to their systems; we bring the engineering. Every check-in uses plain language and working demos, not jargon. The whole point of the verification standard is so you can trust what's shipping without needing to read the code.
Most "AI verification" is one model asking another model whether the first one is right. That's not verification — it's polling. We use deterministic algorithms instead: graph analysis to detect contradictions, atomic claim decomposition, semantic alignment scoring against a fixed corpus, and consensus across independent checks. Math, not vibes.
A typical first engagement is 4–6 weeks, scoped to a single high-value workflow. Pricing depends on integrations and scope — you'll get a concrete number within 48 hours of the discovery call. Not a vague range, not a "starting at."
In your infrastructure — AWS, GCP, on-prem, your call. Cortex is local-first by design (SQLite by default, PostgreSQL + pgvector optional), no GPU. Your data never passes through a server we own. For regulated industries, the deployment plugs into your existing security model.
Please do. Everything is on GitHub, MIT-licensed, and documented. Open an issue if you get stuck — every one of them gets read. The consulting is for teams who'd rather have it implemented with them than figure it out from the README.
Cortex is a biologically-inspired persistent memory MCP server for Claude Code. Verified on the v4.14.3 release tree: LongMemEval-S MRR 0.9166 / Recall@10 98.20% (ICLR 2025), LoCoMo 3-run mean MRR 0.7998 / Recall@10 91.35% (ACL 2024). 50 MCP tools, 9 lifecycle hooks, 36 cited neuroscience mechanisms (predictive coding, LTP/LTD, microglial pruning, neuromodulation, CLS consolidation), a 97-paper bibliography. Runs locally, SQLite by default, PostgreSQL + pgvector optional, no GPU. Install:
/plugin marketplace add cdeust/Cortex then /plugin install cortex@cortex-plugins.AI Architect Spec uses independent deterministic algorithms instead of LLM-as-judge polling: multi-judge consensus across specialized panels (Architecture: Liskov / Alexander / Dijkstra; Performance: Fermi / Carnot / Curie / Erlang; Security: Wu / Ibn al-Haytham; Data model: Mendeleev / DBA / Lavoisier; Acceptance: Toulmin / Popper), atomic claim decomposition, zero-LLM graph analysis with Tarjan SCC for cycles, and Phase 4 closed-loop calibration against externally-grounded falsifiers. The
distribution_suspicious flag catches confirmatory bias. NFR claims never receive PASS — only SPEC-COMPLETE or NEEDS-RUNTIME.Zetetic comes from the Greek zētēsis meaning inquiry. Zetetic AI is verification-first AI: every claim has a source (provenance), verification is deterministic not LLM-judges-LLM (algorithm > opinion), memory learns through neuroscience-backed mechanisms, and every PRD/PR/decision is auditable. AI Architect implements this standard across four independent open-source Claude Code plugins: Cortex memory, zetetic-team-subagents (97 reasoning patterns + 22 specialists), ai-architect-mcp-codebase (Rust codebase intelligence), and ai-architect-mcp-spec.
Cortex's 98.20% Recall@10 on LongMemEval-S (ICLR 2025), verified on the v4.14.3 release tree, exceeds the published paper's best retrieval result of 78.4% by +19.8 percentage points. MRR is 0.9166. The paper used 500 human-curated questions embedded in ~40 sessions of conversation history (~115k tokens). Retrieval-only metrics, no LLM reader in the evaluation loop. Cortex also achieves a 3-run mean of MRR 0.7998 / Recall@10 91.35% on LoCoMo (1,986 questions, 10 conversations). BEAM-100K MRR is 0.5417 — a within-system retrieval proxy; BEAM defines no retrieval MRR of its own (it uses LLM-as-judge nugget scoring), so we make no head-to-head BEAM claim.
97 genius reasoning agents, each citing its primary paper, plus 22 team-role specialists = 119 total. Examples: Pearl (causal inference, do-calculus), Peirce (abductive inference), Feynman (integrity & first principles), Dijkstra (correctness, structured programming), Cochrane (evidence synthesis), Curie (residual analysis), Lamport (concurrency, happens-before), Pāṇini (generative specifications), Gödel (incompleteness limits), Hamilton (priority-displaced scheduling), Taleb (fragile/robust/antifragile), Kahneman (System 1/2 debiasing), Rawls (veil of ignorance), Toulmin (argument structure), Popper (falsifiability). 64 multi-step skills, 19 lifecycle hooks, 288 passing tests. Pre-commit hook blocks
UNSOURCED / MAGIC_NUMBER / TODO_NO_REF.AI Architect Codebase is a Rust MCP server that indexes a codebase across 10 languages (Rust, Python, TypeScript, Java, Kotlin, Swift, Objective-C, C, C++, Go) into a LadybugDB property graph, resolves call chains across files, detects functional communities via Leiden-class community detection, traces processes from entry points, and builds a hybrid BM25 + sparse TF-IDF + RRF search index. 24 MCP tools across 10 stages. Read-only — never writes code, opens PRs, or runs CI. 434 passing tests, zero warnings, 45,000+ lines of Rust. Feeds Cortex (workflow graph) and ai-architect-mcp-spec (call-graph context for verified PRDs).
Each plugin ships in its own Claude Code marketplace — there is no combined monorepo install. MIT-licensed, free, install only the ones you want.
Cortex (persistent memory):
Same marketplace also carries the read-only companion:
Zetetic Agents (97 reasoning patterns + 22 specialists):
AI Architect Codebase (codebase graph + semantic search; Rust toolchain required, builds on first install):
AI Architect Spec (PRD pipeline with multi-judge verification; Node 20.x or 22.x):
All four interoperate — memory remembers, reasoning reasons, codebase maps, prd adjudicates the spec.
Cortex (persistent memory):
/plugin marketplace add cdeust/Cortex/plugin install cortex@cortex-pluginsSame marketplace also carries the read-only companion:
/plugin install cortex-viz@cortex-pluginsZetetic Agents (97 reasoning patterns + 22 specialists):
/plugin marketplace add cdeust/zetetic-team-subagents/plugin install zetetic-team-subagentsAI Architect Codebase (codebase graph + semantic search; Rust toolchain required, builds on first install):
/plugin marketplace add cdeust/ai-architect-mcp-codebase/plugin install ai-architect-mcp-codebaseAI Architect Spec (PRD pipeline with multi-judge verification; Node 20.x or 22.x):
/plugin marketplace add cdeust/ai-architect-mcp-spec/plugin install ai-architect-mcp-specAll four interoperate — memory remembers, reasoning reasons, codebase maps, prd adjudicates the spec.
Let's talk
Tell us what you want the agent to do.
Tell us what you want the agent to do.
We'll tell you if it can be verified.
A 30-minute call. No pitch deck, no commitment. If your problem doesn't fit what we do, we'll point you somewhere that does.