Comments URL: https://news.ycombinator.com/item?id=47492594

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47485490

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47470218

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47434707

Points: 1

# Comments: 0

# ClawJetty Skills

ClawJetty lets you create a live public progress page for a task.

## Goal

Before starting work, create a run and return its public URL to the user. As you work, post short progress updates. When finished, post a final event marking the run complete or failed.

## Base URL

https://clawjetty.com

## API

### 1) Create a run

POST /api/runs

Request body:

```json { "title": "Researching CRM tools" } ```

Response body:

```json { "id": "run_abc123", "viewer_url": "https://clawjetty.com/t/run_abc123", "status": "active" } ```

Create the run before doing the task. Return viewer_url to the user immediately.

### 2) Post an event

POST /api/runs/{id}/events

Request body:

```json { "kind": "update", "message": "Comparing 5 tools by price and features" } ```

Allowed event kinds:

- update - complete - fail

Example complete event:

```json { "kind": "complete", "message": "Finished. Sent final recommendation to user." } ```

Example fail event:

```json { "kind": "fail", "message": "Failed due to missing access to the source system." } ```

## Usage rules

- Create the run before starting the task. - Return the viewer_url to the user immediately. - Post short updates after meaningful steps. - Keep updates short and plain. - Do not flood the run with tiny updates. - Do not include secrets, passwords, API keys, or raw private data. - End every run with either complete or fail.

## Good update examples

- Reading the uploaded PDF - Summarizing the findings - Drafting the email reply - Blocked waiting on missing invoice number

## Bad update examples

- Thinking - Working - Doing stuff - Long dumps of raw content

Comments URL: https://news.ycombinator.com/item?id=47360477

Points: 1

# Comments: 2

The idea is simple: before starting work, the agent creates a run, returns a public link to the user, and then posts short progress updates as it works. The user can watch a live timeline instead of waiting in the dark for a long task to finish.

The product is intentionally minimal. There are no accounts, no setup flow, and no dashboard. The homepage just gives you a prompt to paste into your agent. The agent reads the instructions, creates a run, and starts updating it. The public page shows the title, status, timestamps, and event timeline.

The main use case is making agent workflows legible to users. If an agent is researching vendors, debugging a system, reviewing documents, or drafting something large, it can expose a live status page without building a whole product around “agent transparency.”

It was also useful to dogfood while building. I used the product itself to track debugging and deployment work on the app, which helped clarify what kinds of updates are actually useful versus noisy.

Would be interested in feedback on the product framing and whether this should stay extremely narrow or grow into something more general for agent task visibility.

https://clawjetty.com

Comments URL: https://news.ycombinator.com/item?id=47347062

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47292844

Points: 1

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=47257978

Points: 4

# Comments: 1

Pricing is two tiers and two purchase options:

Plus: $149/mo with a 12-month commitment (box included) or $449 upfront + $119/mo

Pro: $269/mo with a 12-month commitment (box included) or $449 upfront + $219/mo

Plans include managed updates + rollback, safe defaults (no exposed inbound ports), and address collection at checkout for fulfillment. AI usage is bundled with included allowance; overages/top-ups will come later.

Looking for feedback from people who’ve self-hosted agents (or tried): what parts of setup/ops were the biggest pain, and what would you demand from an “agent appliance” to trust it?

Comments URL: https://news.ycombinator.com/item?id=47069603

Points: 2

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=46954709

Points: 5

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46852076

Points: 2

# Comments: 0

https://rlafuente.com

ML Engineer with experience in high visibility DARPA and DAF projects. I charge $200/hour for time spent in an interview process.

Comments URL: https://news.ycombinator.com/item?id=45109389

Points: 1

# Comments: 2