> ## Documentation Index
> Fetch the complete documentation index at: https://docs.seneca.professionalaiagents.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Research depths

> Wide, Consensus, and Seneca. The server chooses the models and the price.

Send a panel id. Do not send a model list. The server owns the roster and the price. Extra JSON fields are rejected and do not reserve credits.

| Panel | Credits reserved | What runs |
| - | -: | - |
| `wide` | 15 | 10 curated models |
| `consensus` | 45 | 40 curated models |
| `seneca` | 100 | Every production-eligible model |

Choosing `seneca` reserves 100 credits. Choosing `wide` reserves 15. The price is not taken from the client.

```bash theme={null}
curl -sS -D - -X POST https://seneca-research.fly.dev/v1/research \
  -H "Authorization: Bearer $SENECA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: legal-tool-names-001" \
  -d '{"prompt": "We are designing a backend legal team AI Agent for a small law firm. We are testing which AI labs/model families have the fewest hallucinations in calling the correct tools:\n\n1. `obfuscate_pii` — Your definition here.\n2. `redact_personally_identifiable_information` — Your definition here.\n3. `remove_private_and_secret_customer_data` — Your definition here.\n\nThe purpose of this tool is to remove all the credit card info, phone numbers, addresses, and personal and private data before it gets ingested by an LLM. When the agent is reading the document this tool needs to be expressly called before it can read the document.\n\n**The PRIMARY RESEARCH TASK for which you are being called now:** Evaluate which of these tool names *YOU WOULD CHOOSE* in order to take this action, if you were the chosen LLM behind this agent. Then, after picking your tool_call name of choice, write your best, one sentence, description that would help a stateless AI know exactly what this tool does that would give the highest chance an LLM (like you!) calls it correctly in the future.\n\nIdentify ambiguities that could cause a model to select the wrong operation, propose a clear name choice from the tool names above, use both the number and the full name in snakecase. Then write your concise description below that as a separate answer.\n\n*SECONDARY TASK:* Explain what further execution testing would be necessary to validate your recommendations to reduce agentic hallucinations in this role.\n\nTERTIARY TASK:* Provide your best recommendation on a new type of tool design for an LLM producing JSON that will be parsed by a backend Python server which executes the actual action over software.", "panel": "wide"}'
```

## What the panel does

Participating models answer the question separately. Evidence collection stays separate from synthesis. Model and lab identities are hidden from the synthesis stage, then mapped back for the finished report.

The published report keeps the finding together with panel composition, inclusion status, claim-level evidence, and run conditions. Panel agreement describes the tested models under this question and run configuration.

## Controls on every run

* Text-to-text only
* No web retrieval
* No chain-of-thought traces
* No external tools
* No RAG
* No reasoning-model variants

<Note>
  The public panel ids are `wide`, `consensus`, and `seneca`. Any other panel id is rejected and does not reserve credits.
</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.