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.
- 7
- Registered specialists
- 1+
- Evidence items required
- 0.65
- Low-confidence review point
- 5
- Approval-triggering action classes
Six visible in the console; one background coordinator is not exposed by default
An answer without evidence is rejected before it is shown
Below this on a decision-impacting answer, more evidence is collected before action
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
Ask in context
A query uses your organization's signals, briefs, index state, approved source records, and decision history.
Approved organization access required
- 2
Prepare the answer
The specialist reviews the question, available sources, and your organization context.
Sources and assumptions shown
- 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
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 roadmapCan 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.