Setup guide

Pipeline Agent for Perplexity - stays current by itself

The free Pipeline Agent runs on Perplexity as three plain-text files: set it up once in a Perplexity Space, approve a sample-data test, then trigger each run with the usage prompt and this run's inputs.

What the Pipeline Agent does

If research already happens in Perplexity, this agent turns it into the finished artifact. It applies your approved changes to the pipeline sheet with conflict-safe, auditable updates: current stage, proposed stage, evidence and approval status on every row.

Pipelines drift because updating them is unpaid work. This assistant proposes stage and field updates with the evidence attached and drafts the chasing messages, all pending your approval. The sheet stays true because staying true costs minutes a week instead of a monthly excavation.

Where the Included files go in Perplexity

Create a Space for the job, upload the Included files, and paste the setup prompt into the Space instructions. Run the setup, approve the sample-data test, and start each run in that Space. Save the agent's output where your work lives (Sheets, Docs).

What a run looks like on Perplexity

A run looks like this: you open the Space, paste the usage prompt with this run's inputs, and Perplexity works through candidate-pipeline with cited sources where the job needs them. The output - it applies your approved changes to the pipeline sheet with conflict-safe, auditable updates: current stage, proposed stage, evidence and approval status on every row - is drafted for your review.

Setup, step by step

  1. Create a Space in Perplexity and name it after the job (for example: candidate pipeline).
  2. Upload skill.md to the Space and paste setup-prompt.txt into the Space instructions.
  3. Run the setup; the agent runs candidate-pipeline on fictional sample data first - approve that test before real work.
  4. Start each real run in that Space with usage-prompt.txt and this run's inputs; save the output where your work lives (Sheets, Docs).

Honest limits on Perplexity

Perplexity is research-first: it drafts and reasons well, but writes to your Google Workspace happen where you save the output. File and Space limits depend on your plan.

Questions people ask

Does the Pipeline Agent work on Perplexity?

Yes - the agent is three plain-text files, and on Perplexity they live in a Perplexity Space. The four setup steps below are the whole job: Create a Space in Perplexity and name it after the job (for example: candidate pipeline). Then upload skill.md to the space and paste setup-prompt.txt into the space instructions.

What does the Pipeline Agent produce on Perplexity?

It applies your approved changes to the pipeline sheet with conflict-safe, auditable updates: current stage, proposed stage, evidence and approval status on every row.. Perplexity drafts it with citations where relevant; you save the result where your work lives. Every run waits for your approval before anything is sent, spent, published or scheduled.

Is this affiliated with Perplexity?

No. AI Agent Skills is an independent store. We are not affiliated with, endorsed by, or sponsored by Perplexity or its makers. Platform names belong to their owners; capabilities change, so check Perplexity's current documentation.

Run this agent on another assistant

Microsoft Copilot Hermes Instinct OpenClaw Muse ChatGPT ChatGPT Dots Claude DeepSeek Town Grok Gemini

More recruiters agents on Perplexity

Sourcing Agent Screening Agent Follow Up Agent

AI Agent Skills is an independent store, not affiliated with Perplexity or its makers. Platform names belong to their owners.