Specialist Agents

Analysis that has to show its evidence.

Research support for grid capacity, assets, geopolitics, investment, contracts, and compute costs. Sources appear with each answer.

Source citedThreshold clearedDesk reviewedHuman approved
7
Registered specialists

Six visible in the console; one background coordinator is not exposed by default

1+
Evidence items required

An answer without evidence is rejected before it is shown

0.65
Low-confidence review point

Below this on a decision-impacting answer, more evidence is collected before action

5
Approval-triggering action classes

Capital, contracts, hedges, production operations, and counterparty contact

The specialists

Scoped narrowly enough to state their own limits

Each is scoped to a domain narrow enough that its boundaries can be written down, so the declared limits mean something.

Grid Capacity

Load growth, interconnection queue pressure, ISO/RTO constraints, and power reliability risk.

Coverage: queues, reliability, and grid constraints

Geopolitical Analyst

GPU supply chokepoints, fab concentration, sanctions and export controls, and regional concentration risk.

Coverage: supply, trade controls, and regional exposure

PPA & Transition Risk

Contract, policy, REC, carbon, and sustainability-risk implications of datacenter power strategy.

Coverage: contracts, policy, emissions, and claims

Datacenter Assets

Facility-level operations, cooling efficiency, uptime risk, and workload placement impacts.

Coverage: facilities, cooling, uptime, and placement

Compute Investment

Investability, underwriting risk, capex timing, valuation pressure, and deal implications.

Coverage: capital, timing, valuation, and deal risk

Compute Cost

Compute price curves, regional basis, energy cost exposure, and model-serving economics.

Coverage: prices, regional basis, energy, and serving cost

How answers are prepared

What every answer has to carry

These controls are required for every answer. An answer that does not meet them is rejected.

At least one evidence item

An answer with no evidence is rejected before it is saved or shown.

At least one evidence item is required

Data limits

Each answer identifies important information that was not available for the analysis.

Data limits are shown with the answer

Scope limits

Each specialist stays within its research area and identifies questions that need another specialist.

Restricted claims are defined for each specialist

Human review

Any recommendation to commit capital, sign contracts, alter hedges, change production operations, or contact counterparties routes to a named human approver.

Approval required, with a written reason

Confidence explained

High confidence requires multiple independent sources or a primary government or company source. Rumor and weak correlation must receive low confidence.

Confidence below 0.65 triggers follow-up evidence collection

Specialist handoffs

When a question crosses a boundary, such as geopolitics into grid capacity, the specialist hands it to the relevant specialist.

Handoff rules are defined for each specialist

Lifecycle

From question to approved recommendation

  1. 1

    Ask in context

    A query uses your organization's signals, briefs, index state, approved source records, and decision history.

    Approved organization access required

  2. 2

    Prepare the answer

    The specialist reviews the question, available sources, and your organization context.

    Sources and assumptions shown

  3. 3

    Check the answer

    The service checks the answer before saving it. The answer must include evidence, assumptions, confidence, recommended actions, and handoffs.

    Invalid output is rejected

  4. 4

    Route consequential actions

    Where the output requires approval, a decision record and an approval are created, and the recommendation waits for a named human.

    Named approver and written reason required

Access status

Specialist queries run inside Compute Desk and require an approved organization account. The instruction contract, declared limits, and approval triggers are published here so they can be reviewed before any engagement.

Questions

What reviewers ask

Do these agents operate autonomously?

No. They answer questions and draft recommendations for human review. Any recommendation touching capital, contracts, hedges, production operations, or counterparties routes to a named approver, and nothing acts on its own.

What happens when an agent does not have the data?

The answer lists the unavailable data and the evidence it uses. An answer without evidence is rejected.

Is there a measured accuracy record?

Not one we publish. We do not claim a scored track record, and confidence levels follow a stated calibration policy. They are not a measured hit rate. A scored outcome ledger is on the roadmap and is not in place today.

See the roadmap
Can I add my own data sources?

Yes. You can assign your organization's approved source records to a specialist role. The specialist can then use those sources as context.

Ask one a question you already know the answer to.

The fastest way to judge a reasoning layer is to test it where you can check the work. Bring a question from your own desk.