# Pebble

> Pebble is your AI coworker for hiring. Bring candidate applications, AI resume screening, interview feedback and offer approvals into one connected workflow.

The linked Markdown files are generated from the public pages. Candidate scenarios and interface examples are illustrative. Pebble recommends; humans decide.

## Website and guides

- [OnPebble Recruiting Software | Sourcing, Screening and Offers](https://www.onpebble.ai/index.md): Pebble is your AI coworker for hiring. Bring candidate applications, AI resume screening, interview feedback and offer approvals into one connected workflow.
- [Ideas for better hiring | OnPebble](https://www.onpebble.ai/blog/index.md): Practical guides to AI-assisted hiring, candidate evidence, interview review and human decision-making.
- [A rehearsed interview answer still needs a follow-up | OnPebble](https://www.onpebble.ai/blog/ai-assisted-interview-preparation/index.md): A sample interview exchange showing how common questions and focused follow-ups reveal responsibility and reasoning beyond a polished opening answer.
- [Save the assessment the reviewer saw, and the correction they made | OnPebble](https://www.onpebble.ai/blog/ai-hiring-audit-trail/index.md): A practical review-record design linking application and criterion versions, the saved AI output, a reviewer’s correction and the next decision.
- [An agent can draft the invitation. Who is allowed to send it? | OnPebble](https://www.onpebble.ai/blog/ai-recruiting-agent-approvals/index.md): An approval and execution design for recruiting agents: inspect the exact action, check changed state and handle retries without assuming success.
- [Try AI screening on one opening before you roll it out | OnPebble](https://www.onpebble.ai/blog/ai-screening-pilot/index.md): A workable pilot plan: one opening, an independent human reading, a correction log and a clear decision about whether to continue.
- [The resume sounds impressive. What did the candidate actually do? | OnPebble](https://www.onpebble.ai/blog/ai-written-resumes-evidence/index.md): A worked example of checking an AI-polished resume: separate the claim, the candidate’s contribution and the questions worth asking.
- [The screening task needs the project example. Does it need the whole file? | OnPebble](https://www.onpebble.ai/blog/candidate-data-ai-hiring/index.md): Map the candidate-data route before an AI assessment: retain useful context, limit unnecessary inputs and check logs, exports and generated summaries.
- [Compare a Shortlist With Incomplete Evidence | OnPebble](https://www.onpebble.ai/blog/compare-shortlist-incomplete-evidence/index.md): Compare a hiring shortlist when interviews and CVs leave uneven evidence. Use a worked matrix to identify the questions that could change your decision.
- [“Human reviewed” should mean somebody checked the application | OnPebble](https://www.onpebble.ai/blog/human-review-ai-screening/index.md): Follow one application from an inflated AI summary to a corrected reviewer note and a useful interview question.
- [Turn a Job Description Into Screening Criteria | OnPebble](https://www.onpebble.ai/blog/job-description-screening-criteria/index.md): Turn a job description into screening criteria with a worked product-marketing example, a reusable worksheet, and a test for each supposed must-have.
- [A translated job title can change the whole assessment | OnPebble](https://www.onpebble.ai/blog/multilingual-resume-review/index.md): A worked translation example showing how to preserve original terms, check responsibility and avoid turning a fluent translation into an unsupported hiring claim.
- [A resume must not be able to rewrite your screening instructions | OnPebble](https://www.onpebble.ai/blog/resume-prompt-injection/index.md): A reference architecture for treating candidate documents as untrusted input, validating assessment output and keeping hiring actions under human control.
- [If candidates can use AI, make the exercise test their judgement | OnPebble](https://www.onpebble.ai/blog/work-samples-ai-era/index.md): A ready-to-adapt support exercise: a customer message, an unsupported promise, shared tool rules and a rubric for checking the candidate’s decisions.
- [Recruitment Offer Workflow Software | OnPebble Offer](https://www.onpebble.ai/offer/index.md): Connect interview feedback, offer letters and approvals in one recruitment workflow. Prepare the offer, route it for review and issue it from the candidate record.
- [Pricing | OnPebble Hiring Software](https://www.onpebble.ai/pricing/index.md): Compare Pebble Starter, Growth and Custom plans by company size, with monthly or annual billing, optional add-ons and managed recruitment.
- [AI Resume Screening Software | OnPebble Screen](https://www.onpebble.ai/screen/index.md): Screen resumes against the job description and opening requirements. Review the AI assessment and its reasons before your team decides who moves forward.
- [Candidate Application Intake Software | OnPebble Source](https://www.onpebble.ai/source/index.md): Collect candidate applications from forms, uploads, agencies and configured sources. Keep each application and its source together on the opening.

## Optional

- [Full website text](https://www.onpebble.ai/llms-full.txt): All indexable pages in one text file.
- [Sitemap](https://www.onpebble.ai/sitemap.xml): Canonical HTML pages.
- [Talk to Pebble](https://www.onpebble.ai/#contact): Request a demo.