People & Company Research Agent · Ploid

Give Ploid one clearly scoped people or company research goal. It researches available material and can return a synthesis with supporting research records. Your Agent can then organize comparisons, review citations and keep unresolved questions visible.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use run-a-research-agent-ploid (3a244b6f-7783-498c-8c33-6ef3a3f04015). Connect through https://toolmu.com/SKILL.md if needed and check get_tool for current availability and cost within my authorized budget. Ask only for missing task details. State the target people or companies, date and evidence requirements in one prompt. Use my spend and format choices; use standard with an output schema. Review the returned synthesis and available sources, then separately organize a brief with supported findings and open questions.

Task:
Research [company or person] on [topic] as of [date]. Answer [question], include a source link for each confirmed fact, and clearly mark anything you could not confirm. Keep the report concise.

Paste into your connected AI's conversation.

Connection guide

Up to 7.68 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

Ploid

People & Company Research Agent · Ploid

You receive

Receive a written research synthesis for the people or accounts in your task, with source references and research materials where available. Review what was found and what supports it; your Agent can separately arrange the returned findings into a briefing or comparison.

Start with your task

Research [company or person] on [topic] as of [date]. Answer [question], include a source link for each confirmed fact, and clearly mark anything you could not confirm. Keep the report concise.

What to know

The task does not guarantee complete coverage, contact details or current roles. Findings can remain uncertain or incomplete. A citation or a structured result does not by itself establish that a claim is accurate or up to date.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Research request`body`	`object`	Required	Required object containing your research goal and any spend or result-format choices. Required fields `prompt`
Research goal and evidence standard`body.prompt`	`string`	Required	Write one self-contained goal in 1–20,000 characters. Identify the people or company, dates, desired result and source evidence to request. Minimum length `1` Maximum length `20000`
Supplier spend ceiling in USD`body.max_spend_usd`	`number`	Optional	Optional supplier task ceiling from USD 0.10 to 6.40 in 0.10 steps. Ploid describes a 0.20 default; this is separate from Toolmu credit reservation and settlement. Minimum `0.1` Maximum `6.4`
Structured-result JSON Schema`body.output_schema`	`object`	Optional	Optional JSON Schema for the desired result shape; use standard. Ploid specifies at most 16,000 bytes. It constrains structure, not the truth of findings.
Result format`body.response_format`	`string`	Optional	Choose standard or markdown. Ploid describes standard as the default with text and research artifacts; markdown requests the synthesis as Markdown. Options `standard, markdown`

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "prompt"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "prompt": {
          "type": "string",
          "maxLength": 20000,
          "minLength": 1,
          "description": "The research goal in plain language — one self-contained task stating the outcome and the evidence standard, not a fixed search sequence. Keep the names, companies, domains, dates, and requested output shape explicit; ask for source URLs when facts must be verified; request exhaustive depth only when the task truly needs it. Example: 'Research the current sales leadership at Retool. Return each person's name, current title, LinkedIn URL when available, and evidence URLs. Clearly label anything that cannot be verified.'"
        },
        "max_spend_usd": {
          "type": "number",
          "maximum": 6.4,
          "minimum": 0.1,
          "multipleOf": 0.1,
          "description": "Spend ceiling for this task in dollars. Default $0.20, range $0.10-$6.40 in $0.10 steps; raise it for deep multi-entity research. Billing is the compute actually used, never the ceiling. The USD amounts in this input description are upstream supplier values; Toolmu charges the current catalog credits."
        },
        "output_schema": {
          "type": "object",
          "description": "Optional JSON Schema (max 16,000 bytes) for a validated machine-readable result, returned at data.structured_output. Requires the default standard response format.",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        "response_format": {
          "enum": [
            "standard",
            "markdown"
          ],
          "type": "string",
          "description": "standard (default) = JSON envelope with output text and artifacts; markdown = the synthesis as Markdown text."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

Write prompt as one self-contained task: identify the target, relevant dates, desired result and evidence standard. Prioritize the questions that matter rather than prescribing a fixed sequence of searches. Ploid can use available people and public-web material for the research.

standard is described by Ploid as the default format, containing synthesis text and research artifacts; markdown requests the synthesis as Markdown. Specific supporting materials depend on what the task returns. Keep source references associated with the claims they support.

For a machine-readable result, provide output_schema and choose standard. Ploid specifies a maximum of 16,000 bytes for this JSON Schema and describes the shaped result at data.structured_output. The schema concerns structure; it does not validate the truth of the research.

max_spend_usd is the supplier task ceiling: USD 0.10–6.40 in USD 0.10 steps. Ploid describes USD 0.20 as the omitted-value default and charges for compute actually used. Toolmu uses credits; this input does not replace its current reservation or determine the final settled charge.

Ask for evidence URLs and clear treatment of unresolved claims when those matter to the task. Read any supplied source in its date and entity context. Your Agent can make a comparison or reading list from the result as a separate step; a synthesis does not guarantee complete or current information.

Ploid: API overview

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

State one outcome, the people or company you mean, relevant dates and the evidence needed to accept a finding. For example, ask for supported sales-leadership names and roles with source URLs. A broad request for everything gives less guidance about which questions to prioritize.

People & Company Research Agent · Ploid

People & Company Research Agent · Ploid

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe the research

Set a maximum, if needed

Check the sources and findings

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe the research

Set a maximum, if needed

Check the sources and findings

Questions about this tool.

How should I scope a research prompt?

Does a source link make a finding verified?

Is the supplier USD ceiling my final Toolmu charge?

Can I combine Markdown with an output schema?