Case 08 named the customer's stated topology in its design and did not build
it; every Check passed because none asked for it.
- The catalogue marks the 26 fields that bind a design. The agreed scope lists
the ones the customer stated; what was assumed for them does not bind.
- A requirement says what it comes from. A submission of requirements is
refused when one of the customer's own requirements, or a stated binding
field, is named by none, or when the requirement carrying a choice is not a
constraint with a condition. The existing chain then owes it a Check.
- Generated code may use only the providers the bundle pins: a resource or a
required_providers entry of any other is refused before Terraform runs.
- The guide opens with how much of the design the customer stated, how much
was assumed and how much is unknown.
Not run with real models.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every Execution now begins by agreeing the scope, before requirements.
- A new Phase and Deliverable, produced by a scope analyst with two tools:
scope_read shows what is settled and what is not; scope_set records fields
with where each value came from (the request, the customer's answer, or an
assumption with its reason). Code checks each value against the catalogue.
- With someone present the analyst asks for what is missing; with nobody
present it assumes it, visibly. With no spec it drafts one from the request.
A value the customer stated in the file is changed only by their own answer.
- A submission cannot leave an essential field unknown. Code writes the
completed spec, the data every later Specialist reads, and the information
register, from what was recorded.
- The spec's status follows the Execution: under review, approved, then
locked as a Baseline. A Change request starts from the delivered scope.
- The requirements analyst derives from the agreed scope and no longer asks
for what it settles.
About 80 tests assumed requirements came first; tests/scoped.py runs scoping
ahead of a test's own script, and tests about order and counts are updated.
Not run with real models.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A scope spec is a YAML file of what the customer wants and the facts a design
depends on, complete or partly filled. It sits beside the Intent, which stays
in the customer's words.
- skills/scoping holds a provider-neutral catalogue of 63 fields; the Cloud
provider's bundle supplies the values it allows for the fields left to it.
- app/scope.py reads a spec against the catalogue with no model: it refuses an
unknown field or a value of the wrong type, and yields what is stated, what
is left to the agent, what is unknown and how pressing each gap is. A field
may say ask, decide or not_applicable.
- ExecutionEngine.start(scope=...), /generate, A2A metadata and evaluation
cases accept one. Its statement is the request, its engagement reference
names the Customer case, and its run options apply. A pre-approved start is
refused when an essential field is not settled.
- The spec as supplied is kept unaltered beside a completed copy with
assumptions, gaps, provenance, readiness and a status.
- Every Specialist is shown the spec and given the Skill: a stated choice
binds, exclusions are out of scope.
- Covers workloads and platform foundations; case-08-landing-zone starts from
a benchmark spec.
Plans for scoping (iteration 9) and the work breakdown structure (iteration
10, nothing built), and the design spec they come from. Not run with real
models.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Case 03's request once each way, both at 100%. Opted in, a module was used
for private Cloud SQL only and 14 Checks were met through its inputs. The
difference in time and cost between the two runs is their Revisions, not
the modules.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Infrastructure code is plain resources by default. An Execution may opt in
with terraform_modules; the deployment default is TERRAFORM_MODULES, off.
- A module is accepted only from the registry namespaces the provider bundle
lists (terraform-google-modules), at one exact version. Any other source is
refused before Terraform runs; until now nothing stopped generated code
naming any source for terraform init to download.
- terraform_module looks up a module's inputs, outputs and submodules from
the registry and says when it cannot be used with the pinned provider.
- skills/google-cloud-iac-modules: when a module fits, and four modules with
examples a test validates against hashicorp/google 8.6.0.
- Opted in, the IaC author and validator get the Skill and the lookup. Not
opted in, they get neither and a module block is refused in code.
- A Change request follows its Baseline. execution.json records the choice.
- case-07 runs case 03's request with modules opted into.
Azure (aztfm) and AWS (terraform-aws-modules) sources are recorded in the
plan for when those Cloud providers are added. No case has run with this.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Schema review: a dotted path is judged only when it starts at a name the
resource type has, so a database flag or a service name is no longer read
as a missing setting. Lesson L-04, which worked around that, is retired.
- Skill routing: in a Change request the question says what changed.
- Evaluation: a case may list code_standards the infrastructure code must
meet; case 06 checks its overlay's regions, naming and labels.
- Model tiers (iteration 5 step 6): a lighter model for a role's first
attempt, named in the provider bundle. Measured on case 03 and left off:
Flash saved five cents on the IaC author and took twice the requests.
- Steps 7 and 9 decided against on the numbers, recorded in the plans.
- Plans: the runs of cases 05 and 06, and the first proof of the lessons on
case 03 (no Revision, 22 minutes against 28, quality held).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Iteration 4:
- Overlay Skills (step 12): an Execution names an organisation's standards
Skill from the folders the deployment configures; recorded with its version.
An example standards Skill and an evaluation case that uses it.
- Lessons (step 10): a prove command that compares a run with lessons against
one without, and triage of evidence an existing lesson already covers.
Iteration 5:
- Step 8: the references of a Specialist's Skills its task needs are named in
its context as read_first.
- Step 14: a remote MCP server's reply that instructs the agent is withheld;
the user's own text is flagged as a risk and nothing more.
- Step 15: in a Change request, items only reworded are listed apart from
real changes.
- Step 19: each Execution's design recommendations are judged when it ends and
the scores kept in its record. The evaluation takes its rubric from the same
place.
Each question was calibrated against live Jev; none has run in a case. Steps
6, 7, 9, 13 and 18 stay planned, with the reasons in the plan map.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Capture, distil, review, publish, retire (ADR-0004). Lesson candidates of
past Executions are grouped into what recurred; a lesson-curator role,
outside any Execution, proposes a lesson per group worth one; each proposal
is an issue file a person approves or rejects; an approved lesson is
written into the provider's lessons Skill, which a Specialist is given only
once it holds lessons for that Specialist's Deliverable. LESSONS_ENABLED
off runs without them, for an evaluation with and without.
The curator proposed six lessons from 21 Executions. The owner approved all
six on 2026-10-09 and they are published: five for the target architect,
one for the IaC author. None is proved by an evaluation yet.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The change-case check asked for a changed Check whose source is the changed
requirement. A functional requirement is carried by the components that
serve it, so it is reached through a Check on an Element realising one.
Plans record the first Change request with real models: a retention change
made in 18 minutes for a third of its Baseline's tokens, touching seven
Checks on one Element and nothing else, and the regression runs of cases
02, 03 and 04, all at 100%. Iteration 7 is complete.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A caller restates a request to say how requirements have changed, naming a
completed Execution of the same Customer case as the Baseline.
- app/baseline.py reads a Baseline from its files and refuses one that
does not exist, did not complete or belongs to another case, before
anything runs or is recorded. A Baseline is never modified.
- Requirements carry a change (unchanged, added, changed, removed) and a
reason. Submission is refused when a Baseline requirement disappears, an
id is reused, or an unchanged requirement's text differs. A removed
requirement stays on record and asks nothing downstream.
- Each Specialist starts from its delivered version; the graph and the code
are its working copy, and the description is carried over when the
design's shape is the same.
- app/workflows/changes.py compares versions by id and traces what each
changed requirement reaches; anything else that changed is listed as
unrequested. Approvals show the change for their Phase, and changes.json
is written with the full Deliverables.
- Intake no longer starts a message read as a change: it names the
Execution to give as the Baseline.
- A fifth evaluation case runs a request and then a change to it, with
four checks that the change is recorded, reaches Checks, stays contained
and costs less than its Baseline.
Tested with scripted agents only; no Change request has run with real
models.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Case 04 (interactive)
- A scripted answer may name who it is for, so facts written for
requirements discovery are not given to a Specialist confirming a draft.
- A reply that restates what the agreed requirements already say is read
as an answer, not a request for changes.
- With a user present, a first submission is refused until the user has
been shown a draft of that Deliverable (CONFIRM_DRAFTS).
Routing and reviews
- Intake: a message that starts something is read first. A question is
answered and starts nothing; a change to delivered work starts as a new
request with a note, until Change requests are built.
- Requirements and recommendations list what infrastructure code can show
(conditions) apart from what it cannot (outside_code); the latter needs
no Check and validation proposes nothing for it.
- A requirements review, "names no products", behind its own switch (off).
- Each pillar advisor reviews its pillar's checklist; the engine writes the
reviews into the design recommendations. The judged checklist check went
from 9-45% a pillar to 100% in one run of case 04.
Evaluation
- Per-case thresholds for Revisions, seconds and tokens, set from every
completed run on this build.
- A progress file after every agent run, so an interrupted run keeps its
time and tokens.
- eval/calibrate_judge.py with a 32-question set awaiting a person's
labels. Unlabelled: Jev stable at 1.00, Gemini 0.92, agreeing on 0.91.
Smaller
- An Execution that ends with warnings writes its Deliverables, with the
warnings and each status in the manifest.
- CI installs the application's dependencies before linting and testing.
- A load-balancer pattern in the IaC patterns Skill.
Plans record nine runs of 2026-10-08. Iteration 6 is complete.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Case 04, the first interactive evaluation, stopped at 100 Orchestrator
turns on two router faults:
- A reply that quoted the agent's question back was judged on that question.
A reply now reaches the router with quoted questions and Q:/A: labels
removed, and the questions are given to the decider as background.
- At a Revision limit the reply was read as another change request for the
same Deliverable, and the refusal repeated. The user is now told once,
the reply is taken as the answer, that Deliverable is not reopened again,
and the Execution carries on with it as it stands.
- Any run that asks the user four times running with no work done in
between now ends with a warning.
The validator is told to confirm with the user in an interactive Execution.
Plans record the fixes and the rerun, which did not finish: both fixes
held, and a third fault appeared that is not fixed here. A scripted answer
restating a requirement, given to a draft-confirmation question, reopens
requirements.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Validator budget 15 to 30: recording verdicts in pieces for 100 Checks
used all 15 calls in one attempt.
- Plans record three runs on 2026-10-08:
case 02 completed at 100% with no Revision in 24 minutes;
case 03 completed at 100% with two Revisions of the design in 40 minutes;
case 04 (interactive) ended with warnings at 75%, on two router faults:
a reply that echoes the question is read as a change request, and the
router loops at the Revision limit. Neither is fixed here.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From the case 02 run cancelled at 66 minutes on 2026-10-07:
- The validator records verdicts a few Checks at a time (verdict_put) and
they are attached on submission. It timed out five times writing them in
one reply. Verdicts on the same code survive a run cut short; verdicts on
changed code are dropped. Its model timeout is 300 s.
- A schema review at submission, in code: every setting a Check names is
looked up on its Element's resource type, and an unknown resource type is
reported. Two Revisions in that run were for Checks no code could meet.
On the two designs that passed validation it raises 2 of 96 Checks, both
one metric name used as a value, so it is returned once and never blocks.
- Reviews run together; the Jev coverage review stays off.
Plans record both steps and the cancelled run.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
After case 02 (completed at 100%, but with two Revisions of the Target
architecture for gaps validation found one pass at a time):
- A Deliverable stands while what it was written from is unchanged. The
architecture description is written from the Elements and Relationships,
so a Revision that only adds or rewords Checks no longer runs the describer.
- Non-functional requirements and recommendations list their conditions,
one entry per separate thing that must be true; submission requires them.
- A coverage review at submission (JEV_COVERAGE_REVIEW, off by default):
for each condition, Jev chooses which Check verifies it, or none. Asked as
one broad yes-or-no per requirement it could not tell a complete design
from one with known gaps; asked as a choice per condition it raised all
four known gaps of case 02 and nothing on the complete graph. An opt-in
live test (LIVE_JEV=1) repeats that.
- The validator is told to report every gap in its first pass.
Plans record the case 02 run and both forms of the review with figures.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Start-up
- Export the env file's variables for other libraries (the Cloud provider's
client) into the process environment; the app's own settings and secrets
are never exported, and a value already in the environment wins.
- Use GOOGLE_GENAI_USE_ENTERPRISE in place of the deprecated
GOOGLE_GENAI_USE_VERTEXAI.
Target architect
- Look each distinct resource type up once instead of once per setting: in
the run of 2026-10-07 it made 39 lookups for 8 types and exhausted its
budget. terraform_schema's find takes several names; budget 30 to 45.
- A cut-off schema outline says so.
Removed, as leftovers of the original pipeline that nothing read
- terraform/ (no longer passed terraform validate), scripts/validate.sh,
tests/test_package.py and the CI steps that ran on them.
- The sample outputs under docs/ and requirements.yaml.
- CI now pins Terraform 1.14.3, as the container image does.
Plans record the case 01 run: completed at 100% in 18 minutes with no
Revision, against 60 minutes and warnings before.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Design is now approved before any infrastructure code is written (ADR-0005).
A new target-architect Specialist produces one graph of Elements,
Relationships and Checks; the diagram is rendered from it, deployment
guidance must account for every Check, and validation gives a verdict per
Check. Requirements, components, products and recommendations carry ids in
data files, and a submission with a gap in the Requirements chain is refused.
Also in this commit:
- Customer cases group Executions, with an intent history per case
- lesson candidates are captured when an Execution ends
- evaluation gains chain, verdict, judged and interactive checks, and
per-case thresholds
- Terraform providers are cached between checks
- the requirements analyst proposes defaults instead of asking
- the legacy-baseline case and the checks that only read it are removed
- ADR-0006 (Change requests) accepted; ADR-0004 and ADR-0007 proposed
- plans for iterations 4 to 7 under .agents/plans/
Unproven with a real model: no evaluation run has completed on this design.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>