Agent-native prospecting · evidence first
Give your AI agent an ICP, a territory, and the evidence standard. Unify GTM returns structured research with source context and review states—without forcing another seat-based workspace into your stack.
Copying is step one; you still run and configure the skill in your agent.
npx -y @okki-global/okki-go-taroball
Agent-native capabilities
Specify territory, company attributes, technologies, buying signals, exclusions, and evidence thresholds in one task. Observations remain separate from inference, so a reviewer can challenge why an account qualified.
Single-source and waterfall enrichment have different cost, coverage, freshness, and deletion implications. Unify GTM frames every supplied field as provider-dependent evidence instead of hiding multiple lookups behind a universal accuracy claim.
Research, contact choice, drafting, approval, and sending remain distinct states. Teams can inspect relevance, suppression, consent obligations, SPF, DKIM, DMARC, and sender reputation without granting the agent automatic outreach authority.
Built around revenue decisions
Challenge a segment thesis with source-backed signals before adding another software seat.
Build focused shortlists while keeping contact choice and outreach under human review.
Compare provider provenance, rate limits, freshness, deduplication, and CRM write behavior.
Compose agent tasks, secrets, APIs, exports, retries, and observable review states.
Separate client credentials, ICP rules, suppression lists, outputs, and audit trails.
Execution timeline
Lock the ICP, exclusions, sources, output schema, and acceptance standard.
Collect public signals and configured enrichment while preserving timestamps and provenance.
Inspect weak matches, unknown fields, regional restrictions, and provider assumptions.
Export or draft only after a person approves the result and downstream permissions.
Four-state runbook
npx -y @okki-global/okki-go-taroballSuccess signal: the exact command is in your clipboard.
Paste the command into the terminal used by your supported AI-agent environment. Read the package prompt before allowing execution.
Success signal: the installer completes without a package or permission error.
Add only the provider credentials your chosen workflow requires. Keep keys in the runtime secret store; never paste them into prospecting prompts.
Success signal: the agent can enumerate the installed skill without exposing secrets.
Begin with a narrow ICP and request evidence fields. Review sources, uncertain matches, and exclusions before exporting or drafting outreach.
Success signal: a structured sample appears with reviewable provenance.
Install FAQ