Encoding Loop Starter Kit

Free Resource

Build the loop the agent runs on — at firm scale.

OpenAI's forward-deployed engineers spent six months embedded inside Thrive Holdings' 30-firm Crete network to build a 97% self-improving tax agent. You cannot replicate that at any price. But the encoding loop the agent runs on sits one layer down the stack — and it fits in your sprint. This kit is the toolkit your AI Champion uses to stand up the first loop in 90 days.

Loop diagram + 8-page How-To
Correction Capture workbook (Excel)
Champion role spec + 90-day roadmap

The Problem

You can't build the agent. But you can build the loop it runs on.

Three pieces of what Thrive built sit outside any 10-person firm's reach. The 7,000-return training corpus assembled across 30 firms. Six months of embedded OpenAI engineers writing evaluation suites and code modifications. A Codex-written self-improving update mechanism. Chasing the cheap version of that stack is the fastest way to waste a quarter.

The mechanism Crete's flywheel runs on is structural, not technological. Corrections become captured production traces, traces become evaluations, evaluations become an updated agent, and the cycle repeats. At your scale, the same loop runs one layer down: corrections become captured rows in a shared sheet, the sheet becomes encoded firm methodology in Claude skills, prompts, and SOPs, and the encoded methodology runs against commodity AI that gets meaningfully better every month on the work you actually do. Discipline, not capital — and that's a fight your firm can pick.

What's Inside

Five components. One operating system.

Everything your Champion needs to stand up the first encoding loop and finish the quarter with rules competitors can't copy.

PDF

1. The Loop, one page

A branded diagram placing the Crete/Thrive vendor-scale loop next to the firm-scale loop on the same architecture. Use it internally to explain that you're running the same shape at a different layer of the stack.

Excel

2. Correction Capture workbook

Three working sheets — the Correction Capture Log with Pattern key + Times seen auto-counting; the Vertical Narrowing Worksheet (volume × similarity scoring); the Encoding Backlog with status tracking. Multi-client. Pre-populated with worked CAS examples.

PDF

3. Champion role spec

A one-page role definition framing the Champion as the firm's forward-deployed engineer — the OpenAI Deployment Company / Tomoro / PCAOB / PwC institutional pattern at firm scale. Usable as an internal hiring spec or role-clarification document.

PDF

4. 90-day first-loop roadmap

Three 30-day phases with weekly checkpoints and numeric exit criteria. Phase 1 capture, Phase 2 encode the first three, Phase 3 measure and defend the role. Explicit kill criteria so a vertical that isn't producing encodable signal doesn't quietly absorb a year.

PDF

5. 8-page How-To

Binds the four artifacts together. Loop explainer, the four-step run guide, capture discipline, encoding placements (Claude skill / prompt / context file / SOP), measurement, and a full cross-reference to the QC Starter Kit so the two kits work as one operating system.

Source files

+ Editable markdown

The Champion role spec and 90-day roadmap are also included as plain markdown — drop them straight into your firm's wiki, edit them in place, and version them with your other operating docs.

How It Works

Four steps that turn corrections into encoded firm methodology.

1. Pick the vertical, not the firm.

Score 3–5 candidate workflows on frequency, repetition across clients, and pass/fail clarity. The highest scorer is your first loop. The instinct to encode the whole firm is the wrong instinct — Crete's 7,000 returns weren't 7,000 different things, they were 1040s and 1041s, repeated.

2. Capture during the work, not after.

Every correction logged in real time, tagged with a short Pattern key. The biggest failure mode is "I'll log it later" — you won't. Be specific in "Why the AI was wrong" and "Firm-specific rule it missed." Generic categories don't produce encoded rules.

3. Encode when Times seen ≥ 2.

One-offs stay in the log as evidence. Recurring catches (the auto-counted Times seen column) earn an encoded rule — a Claude skill, a prompt template, a client context file, or a referenced SOP. The senior on the vertical signs off before each rule ships. This is the moat.

4. Measure monthly.

Two numbers: corrections-per-job (leading indicator — trends down as rules accumulate) and time-on-job (lagging indicator — follows by 2–4 weeks). Both flat after 6 weeks = kill criteria triggered. Both trending down = open a second vertical in Q2.

Download the full kit (ZIP)

Two halves of one operating system

Pairs with the QC Starter Kit.

If you're running the QC Starter Kit, each catch in its Correction Log becomes a candidate row in this kit's Correction Capture Log. QC Kit = Layer 6 (catching errors review by review). This kit = Layer 4 (turning those catches into encoded methodology that makes the same correction stop recurring). Same loop, different surface.

See the QC Starter Kit

Stay Current

Get the kit — plus weekly AI briefings for CAS.

Subscribe to The AI Accountant newsletter and get the Encoding Loop Starter Kit delivered to your inbox, along with weekly analysis of the AI developments that matter for your practice.

Your Move

Start the loop this quarter.

A firm running its own encoding loop builds a moat that thickens every month. A firm waiting for the vendor-built agent generates the training data the vendor will eventually sell back to it. The difference in eighteen months isn't a benchmark point on a model release page — it's whether the work your team does still belongs to your firm.