The TalentPrism CLI is an API-backed command-line interface for humans and shell-capable AI agents. It provides stable JSON output, structured errors, team-scoped API-key access, recruiter-assistant workflows, and safe draft sequence creation without browser automation.
Agent-readable command reference
Use tp when an agent needs to inspect TalentPrism sequences, candidates, interviews, reminders,
campaign summaries, activity summaries, metrics, copilot briefs, or create a draft sequence through the same Django-backed permissions
and validation used by the web app.
Install
After the package is published, install the CLI with a Python tool installer:
pipx install talentprism-cli
uv tool install talentprism-cli
For local development from the fleetapp repository:
python -m pip install -e .
Authenticate
Create a team-scoped API key from your TalentPrism profile, then set these environment variables:
export TALENTPRISM_BASE_URL="https://talentprism.ai"
export TALENTPRISM_API_KEY="<your api key>"
TALENTPRISM_API_KEY is the preferred auth path for agents because it does not require writing
secrets into a local config file. API keys are scoped to one TalentPrism team.
Common Commands
tp config get
tp whoami --output json
tp sequences list --output json
tp sequences list --status Active --output json
tp sequences show <sequence_uuid> --output json
tp sequences summary <sequence_uuid> --output json
tp candidates list --sequence <sequence_uuid> --output json
tp candidates engaged --sequence <sequence_uuid> --output json
tp candidates search --query "aircraft assembler North Charleston" --json
tp candidates show <candidate_id> --output json
tp candidates show <candidate_id> --conversations --reminders --json
tp candidates add-note <candidate_id> --text "Prefers second shift" --json
tp candidates send-email <candidate_id> --subject "Next step" --body "Please use your interview link." --confirm-write --json
tp candidates send-sms <candidate_id> --message "Reply 1 to fast-track." --confirm-write --json
tp reminders list --owner <user_id> --due today --json
tp reminders create --candidate <candidate_id> --due tomorrow --text "Call about availability" --json
tp reminders complete <reminder_id> --json
tp capabilities list --json
tp capabilities mcp --json
tp capabilities commands --json
tp capabilities invoke candidates.search --input-json '{"query":"aircraft assembler"}' --json
tp capabilities invoke candidates.add_note --input-json '{"candidate_id":123,"text":"Prefers second shift"}' --confirm-write --json
tp campaigns summary <sequence_uuid> --json
tp campaigns next-actions <sequence_uuid> --json
tp campaigns deliverability <sequence_uuid> --json
tp copilot brief --recruiter <user_id> --since yesterday --json
tp copilot ask "What changed in the aircraft assembler campaign?" --json
tp interviews list --sequence <sequence_uuid> --output json
tp interviews show <interview_uuid> --output json
tp interviews create-link --candidate <candidate_id> --sequence <sequence_uuid> --confirm-write --json
tp recruiters notify --candidate <candidate_id> --sequence <sequence_uuid> --update "Candidate asked for a callback." --confirm-write --json
tp metrics --output json
tp metrics --sequence <sequence_uuid> --output json
tp activity summary --days 14 --output json
tp activity summary --days 14 --sequence <sequence_uuid> --json
tp chats summary --days 14 --json
tp chats summary --days 14 --sequence <sequence_uuid> --json
tp chats messages --chat-id <chat_id> --json
tp sequences create --dry-run --file sequence.yaml
tp skill print
Use tp capabilities list --json to discover the current typed Agent Capability registry,
including schemas, source policy, risk, and field policy metadata. Use
tp capabilities mcp --json when an agent framework needs MCP-style tool metadata generated
from the same registry. Use tp capabilities commands --json to generate
tp capabilities invoke ... examples from the live registry. Use
tp capabilities invoke <name> --input-json <json> for registry-driven execution;
write capabilities require --confirm-write and are rejected without it.
Draft Sequence Creation
tp sequences create --file <path> accepts YAML or JSON files with explicit
step1, step2, and step3 sections that mirror the TalentPrism
sequence wizard APIs. New sequences remain in Draft.
tp sequences create --dry-run --file sequence.yaml
tp sequences create --file sequence.yaml
tp sequences update-step2 <sequence_uuid> --file sequence.yaml
tp sequences update-outreach <sequence_uuid> --file sequence.yaml
Output and Errors
Successful command data is written to stdout. Errors and progress notes are written to stderr. Output defaults to JSON when piped and table output in an interactive terminal.
tp metrics --output json
tp activity summary --days 14 --output json
tp chats summary --days 14 --output json
tp sequences list --output yaml
tp candidates list --sequence <sequence_uuid> --output csv
Structured error payloads include:
{
"code": "auth_failed",
"type": "auth",
"message": "TalentPrism rejected the API key.",
"details": {},
"remediation": "Verify TALENTPRISM_API_KEY is active and scoped to the expected team."
}
Exit Codes
0: success2: invalid input3: auth failure4: not found5: validation failure6: transient service failure7: schema mismatch
Safety Boundaries
The CLI reads TalentPrism data, creates and completes reminders, adds recruiter notes after explicit write confirmation on the generic capability path, runs copilot planner prompts, and creates or repairs draft sequences. It does not send outreach, trigger voice calls, activate sequences, delete data, or bypass Django permissions.
Bot and Agent Access
This page is public and does not require a TalentPrism login. Public crawlers, documentation checkers, and agent-readiness tools can use it to discover the install, authentication, command, error, and safety contract for the TalentPrism CLI.