CONTEXT(CLONE)
Sign in

Trace grid code and tariff changes to every affected asset

For: Grid compliance or regulatory affairs manager at a generator, storage operator or network company

Pattern: WatchtowerNeeds a connectorDesigned for 20 to 500 agents
Get early accessSign in to use

The pain today

A revised grid code clause or tariff schedule touches some assets and not others, depending on connection date, voltage level, technology and derogations. Working out which means a manual pass over every connection agreement.

The ask

“Here are our connection agreements, compliance statements and derogations for every site, and the grid code and tariff documents they refer to. When a clause or schedule changes, tell me which sites it applies to, what each site's documents say today, and where the new text asks for something the site has not declared.”

Plain words, as you would say it to a colleague. Edit it to fit your case before you send it.

What you attach or connect

  • Connection agreements and derogations per site
  • Compliance statements and declared capabilities
  • Grid code, tariff schedules and consultation drafts
  • Site register with voltage level and connection date

The unit of work

One worker task per one changed clause against one site's documents.

Why a swarm fits

Many clauses times many sites gives a wide grid of small checks. When one clause changes, only the sites that fall under it are redone, and each check needs one clause and one site's papers.

Not for

Proving a plant meets a technical requirement. It compares documents; it does not run simulations or read test measurements.

The decision tree

6 typed decisions, each with an action for every answer

At fixed moments in a run, the engine puts one narrow question to a decision model. The decision model never writes text: it answers yes or no with a probability, picks from listed options, or gives a score, about a small slice of the material. The engine then does exactly what this tree says, which is what makes the run auditable. The thresholds are the template's design values, not measured results.

  1. Planner, while planning

    Scope checkA choice among options

    Before work starts on a unit

    Does the changed clause name a technology, voltage level, capacity band or connection date range that appears in our site register?

    Sees only: The changed clause's applicability text and the site register's column values

    Why: Drops changes that cannot apply to the fleet before any site is re-read.

    • Names a class we operatethenAccept
    • Names only classes we do not operatethenSkip this unit
    • Applicability not stated in the clausethenEscalate to a strong model

  2. After workers, the judge checks

    Evidence checkYes or no, with a probability

    After a worker answers

    Does the new clause text differ from the old in a requirement, a value, a deadline or who it applies to?

    Sees only: Old and new text of one clause

    Why: Separates renumbering and editorial edits from changes that create work.

    • Yes: 0.85 or higherthenAccept
    • Unsure: 0.50 up to 0.85thenEscalate to a strong model
    • No: below 0.50thenReject and retry

  3. Evidence checkA choice among options

    After a worker answers

    Does the site's compliance statement declare the capability the new clause asks for?

    Sees only: The new clause and the matching section of one site's compliance statement

    Why: Shows the gap between the new text and what the site has declared, without judging the plant.

    • Declares itthenAccept
    • Declares something differentthenMark unresolved
    • SilentthenMark unresolved

  4. Evidence checkYes or no, with a probability

    After a worker answers

    Does the quoted derogation cite this clause number and remain within its stated validity period?

    Sees only: One derogation letter extract and the changed clause number

    Why: Applies derogations before a gap is reported, so known exceptions are not raised again.

    • Yes: 0.85 or higherthenAccept
    • Unsure: 0.50 up to 0.85thenEscalate to a strong model
    • No: below 0.50thenReject and retry

  5. Run control, between rounds

    Another round?Yes or no, with a probability

    Between rounds

    Have all sites selected for this changed clause been compared, with no new publication received since the round began?

    Sees only: The site check list for this clause and the publication log

    Why: Ends the round cleanly and redoes nothing that the change did not touch.

    • Yes: 0.70 or higherthenStop
    • Unsure: 0.40 up to 0.70thenContinue
    • No: below 0.40thenContinue

  6. Accountable person, before anything is settled

    Person decidesYes or no, with a probability

    Before anything is reported as settled

    Does the finding suggest a site's documents do not meet the new clause, or that applicability to a site is arguable?

    Sees only: One site impact with clause and document quotes

    Why: Any statement about a site's compliance belongs to the compliance manager and a licensed engineer.

    Accountable: The compliance manager and a licensed engineer own any finding of non-compliance and every derogation request or notice to the operator.

    • Yes: 0.40 or higherthenAsk a person
    • Unsure: 0.15 up to 0.40thenAsk a person
    • No: below 0.15thenAccept

The fleet: who does what

Model tiers by role, not brands: you choose the models. Strong reasoning models plan and reconcile, small fast models do the wide work, and the judge is a decision model from a different family, so it does not share the workers' blind spots.

  1. Planner

    A strong reasoning model reads each change, works out its applicability rules and selects the sites that fall under it.

    Decisions here:1. Scope check

  2. Workers

    Small fast workers from an open-weight family compare one changed clause with one site's agreement and declarations.

    Designed for 20 to 500 agents, one worker task per one changed clause against one site's documents. Each worker receives only its own unit.

  3. Judge, from a different model family

    A decision model from a different family checks that applicability and each claimed gap follow from the quoted texts.

    Decisions here:2. Evidence check3. Evidence check4. Evidence check

  4. Reconciler

    A strong reasoning model groups impacts by clause and site and keeps cases where applicability is arguable.

    Decisions here:5. Another round?

  5. Accountable person

    The compliance manager and a licensed engineer own any finding of non-compliance and every derogation request or notice to the operator.

    Decisions here:6. Person decides

Checked before anything is accepted

  • Each impact quotes the old clause, the new clause and the site document
  • Applicability is tested against the site register before any comparison
  • Derogations are applied before a gap is reported

What comes back

  • Impact list per changed clause with affected sites
  • Per-site gaps between new text and declared capability
  • Sites where applicability is unclear, with both readings
  • Draft points for a consultation response

What to measure

  • Impacts confirmed by the compliance manager
  • Time from publication to impact list
  • Affected sites found later that were missed
  • Cost per change processed

Names of measures only. No result is claimed for this template.

Templates open in the workspace chat with the ask filled in. Nothing runs until you send it.

Get early accessSign in to use

More in Energy and utilities

Reconcile study assumptions across an interconnection queue

For: Interconnection manager at a developer, or a transmission planner reviewing clustered studies

Each project's study rests on a base case, on earlier-queued projects assumed in service, on short-circuit levels and on shared network upgrades.

Pattern: Map, verify, reduceNeeds scale6 decisionsDesigned for 30 to 400 agents

Check a flexibility contract portfolio against dispatch obligations

For: Portfolio manager at a flexibility aggregator, or a utility demand-response programme lead

Every site contract has its own notice time, duration limit, activation cap, availability window, baseline method and penalty.

Pattern: Specialist panelNeeds live models6 decisionsDesigned for 8 to 300 agents

Review maintenance and test records across a substation fleet

For: Asset manager or maintenance engineer at a transmission or distribution network operator

Oil analysis reports, breaker timing tests, relay test sheets and battery discharge tests sit inside work orders.

Pattern: Hierarchical decompositionNeeds a connector6 decisionsDesigned for 40 to 600 agents