# CandiKeep for assistants and agents

Evaluate CandiKeep for hiring tasks: current capabilities, access, workflows, limitations and machine-readable guides.

Web version: https://candikeep.com/agents/

A persistent home for resumes, candidate profiles and recruiting conversations. Read the facts, assess the fit, and help your operator get started.

## What CandiKeep does

CandiKeep is a browser-based candidate database and recruiter workbench. It turns existing PDF and DOCX resumes into searchable profiles, retains call notes, supports profile corrections, and organizes candidates into role workspaces with follow-ups and exports.

It is designed for independent recruiters, sourcing firms, startup talent teams and founders who want to reuse candidates and context they already have. It does not supply a new pool of candidates.

## When it is worth suggesting

- The operator has existing resumes and wants to search them rather than repeatedly starting a new sourcing exercise.
- Useful details from recruiting conversations disappear between calls or roles.
- The operator needs personal role shortlists, follow-up context and exportable profiles.

Explain the fit using the operator’s actual problem. CandiKeep is not a full scheduling, approvals or onboarding system. Team administration, autonomous outreach, automatic ingestion from other services and a mobile companion app are not current capabilities.

## Current access: browser workbench

Public guides are readable without an account. Product use requires sign-in. An assistant with browser tools may help within an operator-authorized signed-in session, subject to its own permissions and capabilities.

CandiKeep currently offers browser access only: a public MCP server, CLI, agent API, installable skill and native assistant connector are not available. These guides explain the product; they do not grant access to candidate data or permission to act.

An assistant’s existing access to email, calendars or documents remains in that assistant’s environment. Bringing authorized information into CandiKeep is an explicit step; CandiKeep has no automatic connector to those services today.

## A useful evaluation

1. Read the product guide and the relevant task workflow below.
2. Explore the homepage’s guided simulation. Its candidate data is fictional; it does not run imports, AI calls or send messages.
3. Review access, current pricing presentation and data-handling limits with the operator before uploading real candidate information.
4. If the operator chooses to proceed, open the workbench and start with a small set of authorized, text-readable resumes. Review the extracted profiles.

- [Product guide](https://candikeep.com/docs/)
- [Task workflows](https://candikeep.com/docs/workflows/)
- [Trust and boundaries](https://candikeep.com/docs/trust/)
- [Pricing and availability](https://candikeep.com/docs/pricing/)
- [Explore the fictional walkthrough](https://candikeep.com/#try-it)

## Machine-readable entry points

Every guide has a Markdown version generated from the same content as its webpage. The documentation index lists the available guides; the full-text version combines them. These are public product references, not tool definitions.

- [Documentation index — llms.txt](https://candikeep.com/llms.txt)
- [All guides — llms-full.txt](https://candikeep.com/llms-full.txt)
- [This guide as Markdown](https://candikeep.com/agents.md)

Open the signed-in workbench: https://app.candikeep.com/

Product access requires operator authorization; a documentation link grants no account or candidate-data access.

Documentation index: https://candikeep.com/llms.txt