Assessment as Automation
Updated
IntermediateWhat you'll learn
~15 min- Convert assessment from a one-time consulting deliverable into a cheap, repeatable pipeline
- Recognize how AI shifted the disposition calculus: build AND extend got cheap, buy got squeezed
- Connect data-estate readiness to every AI ambition on the roadmap
The economics flipped while nobody renamed the activity
Lesson 1.2 taught the four assessment artifacts as careful, cited work — and they are. What has changed is what they cost. An agent pointed at a legacy repository produces the inventory, the dependency map, the current-state table, and a disposition-candidate list in hours. That is not a smaller version of the old three-week consulting engagement; it is a different kind of thing, and it deserves a different operating model structure:
OLD: assess once, at program start, expensively -> decisions age against a snapshot that is stale by phase 2NEW: assessment is a PIPELINE -- re-run it before every disposition decision, after every major phase, and on a schedule, because it costs an afternoon and cites its evidenceThe four artifacts and the two quality gates (every claim cited, every metric a number) do not change. What changes is the tense: “the assessment” becomes “the latest assessment.”
Prompt first: the standing assessment
Switch your workspace agent to Plan mode on your repository and assessment/ folder, and ask it to plan the next standing assessment run (if you do not have live exports or files handy, ask it to generate a small Meridian practice sample from the lesson’s scenario first):
Re-run our four-artifact codebase assessment and plan a diff against assessment/2026-06.md before writing assessment/2026-08.md. Show what improved with commit evidence, what regressed, and whether this phase retired its target weaknesses.Check that the plan or draft covers:
- Regenerating all four assessment artifacts (current-state table, countable weakness list, numeric success metrics, and risk register)
- Diffing against
assessment/2026-06.mdto show what improved (with commit evidence) and what regressed or newly appeared - Checking whether the weaknesses the current roadmap phase was supposed to retire were actually eliminated
- Writing the updated output to
assessment/2026-08.mdin the identical structure
If the draft overwrites the baseline without producing a delta section, follow up with: Add an explicit diff section comparing each weakness count against assessment/2026-06.md with commit SHAs.
The diff is the point. A standing assessment that tracks its own deltas becomes the program’s honest scoreboard: Lesson 1.4’s roadmap tied phase 3 to retiring specific weaknesses — the frozen runtime, the zero test coverage — and the re-run says whether it actually did.
What cheap assessment does to the disposition calculus
Here is the subtle 2026 shift, and it is not the one most people quote. AI made building cheap — everyone sees that. It also made extending cheap: agent-assisted comprehension and refactoring of legacy code puts the “extend” option back on the table for systems that a 2023 assessment wrote off as too tangled to touch. The squeezed option is buy: COTS licensing and low-code platforms now compete against custom builds that cost days and extensions that no longer cost archaeology.
Two consequences for Lesson 1.3’s framework — the framework itself survives untouched:
- Re-run dispositions when the input costs change. A “replace” verdict from two years ago rested on “remediation is prohibitively expensive.” That premise may simply be false now. The attribute matrix and feature-parity disposition table are exactly as valid; feed them current numbers.
- “Too hard to assess” is an obsolete verdict. The mystery subsystem nobody understood — the one every roadmap routed around — costs one agent-afternoon to map. Route through it.
Authorization, integration, accreditation, and organizational change absorb most of a regulated modernization’s calendar — and none of them compressed. When an AI-era estimate says “we can rebuild this in a week,” read it as “the code takes a week.” The distance from working code to production system is Module 4’s territory, measured in the same units it always was. Lesson 6.4 attacks that bottleneck directly.
The other half of readiness: your data
One assessment target deserves explicit mention because every AI ambition on the roadmap quietly depends on it: the data estate. Module 3 taught contract-driven migration — recipes, dictionaries, control tables, manifests. Notice what that discipline produces: catalogued, contract-validated, provenance-tracked data. That is precisely the substrate LLM-driven tools need — an agent can answer questions against a governed lake with a dictionary; it can only hallucinate against a file share of ambiguous CSVs. When the standing assessment inventories systems, have it inventory data readiness too: which datasets have contracts, which have owners, which are still folklore.
A 2023 assessment marked the scheduling subsystem 'replace -- remediation prohibitively expensive; code impenetrable.' The 2026 roadmap inherits that verdict. What does this lesson say to do?
Key takeaway
Assessment became a pipeline: re-run it before every decision, diff it against the last run, and let it keep the roadmap honest. Feed the unchanged Lesson-3 framework current economics — build and extend got cheap, buy got squeezed, and “too hard to touch” retired as a verdict. And assess the data estate alongside the systems, because everything in the next two lessons feeds on it.