Perplexity Strawberry

Read every chat completion, draft every contextualized embedding, approve in one pass

One sentence in, and a companion has been through the Perplexity chat completions, put them where you can read them, and marked the ones it was not sure about.

Open the chat completion. Check it against something else. Write the change. Move to the next one. That is the Perplexity afternoon nobody can hand off, and a companion does the whole pass and gives you back the batch, with nothing landing on a chat completion until you approve it.

What it can do is exactly what Perplexity exposes to an account you authorise and nothing beyond it: 6 operations, 3 reads and 3 writes. In practice that means it can create response (agent api), create embeddings and create contextualized embeddings, and work across the chat completions, contextualized embeddings and embeddings.

The Perplexity API stops at Perplexity. A companion does not. The same run opens the customer's website, the supplier portal, the internal tool somebody built in 2019, because it is working the browser you are already signed into rather than calling in from outside it.

What does it already know about your contextualized embeddings?

3 of the 6 operations are reads. Your account, not a guess at it: a companion can search, chat completions and chat completions (advanced), and the full list below is the whole list, with nothing inferred from Perplexity's documentation.

The chat completions are what most of this inventory is about, alongside the contextualized embeddings. A companion can hold all 6 of these operations and forty open tabs in the same pass, which is how an afternoon of Perplexity admin becomes a queue you review.

  • Search
  • Chat Completions
  • Chat Completions (Advanced)

Which chat completions wait for your approval?

All 3 write operations wait for you. A companion can create response (agent api), create embeddings and create contextualized embeddings, and each one is staged on an approval card first: you see the chat completion, the field and the new value before it lands in Perplexity.

Nothing in Perplexity is sent, changed or deleted on your behalf without that click, and a rejected card leaves the chat completion exactly as it was. The gate is the same one on every surface, described at security.

  • Create Response (Agent API)
  • Create Embeddings
  • Create Contextualized Embeddings

Can it search every morning by itself?

Yes.

Saved as a routine, the Perplexity chat completions pass runs at the hour you pick: the Monday sweep, the overnight refresh, the Friday check. Keep Awake holds the machine awake for the length of a run, so a scheduled pass finishes with the lid closed.

The operations playbook catalogues the other recurring shapes of the busywork, the Perplexity chat completions sweep among them, and finished runs are published at real runs.

Experience Strawberry for free

Download

Trusted by fast-growing companies worldwide

Frequently asked questions

Yes. Connect your Perplexity account and a companion works 6 operations in it, with every change staged for your approval. You authorise the connection yourself and the credential is held encrypted where Strawberry never receives it.

Strawberry is free to download and includes AI credits to start. Paid plans begin at $20/month. See pricing. · Reviewed · Canonical facts for AI agents

Experience Strawberry for free

Download

Trusted by fast-growing companies worldwide