AgentMesh360 Job Agent · Browser job-search workbench · End-to-end job search

From what's worth applying to, to applying for you automatically,
to practicing until you land it.

A 36-dimension profile first decides what's worth applying to, and selected jobs are then applied to automatically; an AI voice interviewer practices with you until showtime, with a dual-track report that even measures how you say it; 8-stage tracking, offer comparison, and negotiation practice close it out. The whole job-search flow in one browser workbench.

Open the workbench
New-user welcome offer Sign up free and get a 3-day pass + 30 credits

Activates automatically the first time you use any commercial product within 7 days of signing up. Shared across all AgentMesh360 products — no card required, no automatic renewal. The 30 credits cover a resume profile plus your first custom question bank, or 2 platform Discovers.

Works with host Agents like Claude Code / Codex / OpenClawEnter the workbench after subscription verificationInterview recordings auto-deleted after 30 daysPass shared across the ecosystem, no automatic renewal
Today overview: journey metrics · to-do list · recommended next steps My applications: one 8-stage progress line per job, updated live for replies, interviews, and offers Mock interview: a question bank customized to profile × JD, each question with what it probes and follow-up directions Interview report: dual-track content / delivery scores · per-question feedback · improvement suggestions Offer comparison: weighted multi-dimension scoring · explainable recommendations Negotiation practice: anchoring strategy scripts · text sparring with an AI HR
Today overview: journey metrics · to-do list · recommended next steps

Copy the command below and send it to your AI Agent to set up Job Agent and connect your AgentMesh360 subscription.

~ paste-this-to-your-agent
$ curl -fsSL https://raw.githubusercontent.com/jiyangnan/AgentMesh-JobAgent/main/scripts/install.sh | bash
1

Send the command to your Agent

Your AI Agent runs the installation: it sets up the Job Agent Skill and CLI and connects your subscription.

2

Sign up and get a pass

US$4 for 30 days, including 1000 credits shared across the AgentMesh360 ecosystem. No automatic renewal.

3

Enter the workbench

Open the workbench in your browser; once your subscription is verified, your complete job-search flow loads.

Installs the product Skill and CLI adapterDoes not install another AI AgentRecruiting-platform cookies stay on your device
The whole picture

A job search isn't luck —
it's four stages you can train separately.

Installed and signed in — so what's inside the workbench? Three moves: decide what's worth applying to, apply automatically, and practice until you land it. One recruiter-side, 36-dimension profile runs through everything, and every stage gets a concrete tool, so judging, executing, practicing, following up, and deciding all beat going by feel.

Today overview: journey metrics, to-do list, and recommended next steps
Workbench overview · Journey metrics, to-dos, and the next recommended action stay in one place.
StageThe problem you hitThe tool Job Agent gives you
Before applyingNo idea what's worth applying to36-dimension profile × job decisions across four platforms, up to 100 deduplicated jobs judged per run, selected / review / rejected with evidence of fit and verifiable signatures
Before the interviewNervous, no feedback, no idea where you're weak5-dimension custom question bank + live voice practice + dual-track score report
Following upApplications forgotten, follow-ups missedAn 8-stage progress line per job; stalled items are grouped into one account status digest
After the offerChoosing between offers by feel, no negotiation experienceWeighted four-dimension comparison + read-aloud negotiation scripts + practice with an AI HR
ThroughoutScattered tools, scattered accounts, unclear costsOne AgentMesh360 pass works across the ecosystem; credits are billed per action, with no automatic renewal
Job discovery and application decisions · Open-source CLI

It knows what's worth applying to — and applies for you.

Chrome on your device connects to Boss 直聘, 猎聘, 智联招聘, and 51Job, while the cloud's 36-dimension profile judges every job one by one and returns complete decisions in all three categories — selected jobs are applied to automatically in platform order, and you only step in for sign-ins and CAPTCHAs. It shares the same account and the same pool of credits as the web workbench.

i.

Independent workflows per platform

Boss 直聘, 猎聘, 智联招聘, and 51Job each fetch, deduplicate, and judge on their own, so one platform acting up doesn't sink the whole round.

ii.

Automatic applications to selected jobs

Starting a round authorizes applying to selected jobs in order; review is excluded by default and rejected is never applied to — the boundaries are spelled out before you start.

iii.

Checkpoint recovery, never charged twice

CAPTCHAs, sign-ins, and network drops all pick up from where they stopped; failures before the decision aren't charged, and failed cloud decisions are refunded.

AgentMesh360 Cloud · example decision summary
 candidate profile  36 recruiter-side dimensions ready
 candidate jobs      86 normalized and deduplicated
 decision            selected 18  review 11  rejected 57
 personalized greetings 18 grounded in resume evidence
 official result      signature verified
Product demo

A complete four-platform job search in three minutes.

From pasting the install command to a verifiable AgentMesh360 cloud decision, then sequential execution on Boss 直聘, 猎聘, 智联招聘, and 51Job. A real workflow recording, about 3 minutes.

The recording shows the public CLI and sequential execution across all four platforms. Sensitive credentials and local paths are hidden. The video includes music.
Custom question bank · Voice practice

Live voice practice, not text Q&A.

Before the real thing, spend 10 credits to generate a written question bank — 5 dimensions, 10+ questions, charged once per JD — and read it through before you go on mic. The AI interviewer talks with you in real time using neural voice: it has read your resume profile and target JD, usually opens with a project you've worked on, and follows up on your answers instead of moving straight to the next question.

Mock interview: a question bank customized to profile and JD, with probes and follow-up directions
Mock interview · A question bank grounded in profile × JD, with probes and follow-up directions for every question.
i.

Questions built from your experience

Your resume profile + target JD generate a 5-dimension bank — self-introduction, project deep-dives, technical checks, behavioral questions, and your questions for them — each with follow-up directions. Not a generic interview-prep list.

ii.

It follows up in real time

Mention an architecture choice and it asks "why did you pick that at the time?" The gap between finishing a sentence and hearing the next one is about 1.3 seconds — close to the rhythm of a real conversation.

iii.

20 minutes per session

About 12–15 fully structured exchanges. A dual-track report is generated automatically when it ends; you can also generate the question bank on its own and review it in writing first.

Interview report

The report grades two things: what you said, and how you said it.

Generated automatically when the interview ends. The content track scores every question and gives actionable advice; the delivery track is computed from word-level speech-recognition timestamps, not a model's subjective impression. Scores have explicit anchors.

Interview report: separate content and delivery scores, question-level feedback, and improvement suggestions
Interview report · Content and delivery are scored separately, with feedback tied to individual questions.
i.

Every suggestion points to a question number and your exact words

It skips filler like "delivery could improve" — "you said 'you know' 6 times in 15 seconds on question 3" is feedback you can act on.

ii.

Delivery metrics are deterministic

Filler-word frequency, pause distribution, net speaking rate, repeated restarts — measured values that come out identical if you recompute the same interview.

iii.

Score anchors are public

What each score means is spelled out in the report. Vague answers come with "a better answer" examples.

interview-report · dual-track report (sample excerpt)
▎Content track (per-question scores)
Technical depth     4/5  solid project detail
Project experience 3/5  missing quantified results
STAR structure     3/5  results section runs thin

▎Delivery track (measured)
Pace    4.8 words/s  △ a bit fast — aim for about 3.5
Fillers 8.2 /min     ⚠ 6 "you know" in 15 seconds on Q3
Pauses  longest 2.3 s (02:15)

▎Improvement suggestions
Q2 ran 3 minutes in circles → lead with the conclusion, keep it under 90 seconds
The two vague answers include "a better answer" examples
  • Stumbles are pinpointedTimestamped markers take playback to the exact second.
  • Recordings auto-deleted after 30 daysAfter the report is generated, the recording is kept encrypted for 30 days for playback and then deleted automatically — or delete it yourself at any time.
  • It doesn't predict real interview outcomesIt's a practice tool for surfacing weaknesses and training how you speak.
Job-search journey tracking

The applications you send out shouldn't vanish into silence.

Every job gets its own progress line with 8 stages: Applied → Replied → Interviewing → Negotiating → Waiting for offer → Offer received (plus two terminal states, Declined and Closed). You tap once to update a status; the system records the time and computes how long it has been sitting.

My applications: one 8-stage progress line per job, updated for replies, interviews, and offers
My applications · Each job has its own 8-stage progress line, updated as replies, interviews, and offers arrive.
i.

Reminds you when it's time to follow up

Each job is still evaluated independently, but every reminder cycle sends one account digest with the full active-stage summary and only the jobs that need attention expanded. Each stage can trigger at most twice, with quiet hours you can set.

ii.

The day before an interview

You get a "one last practice" nudge with a one-click jump straight into the mock interview.

iii.

Close everything out with one click when an offer lands

Accept the offer and close all other open applications in bulk. Three replies on Boss 直聘 doesn't mean five on 猎聘 — every job is tracked independently.

Offer decisions and negotiation

When you're holding cards, don't play them by feel.

With two or three offers on the table, Job Agent helps you run the numbers and find the right words — and guarantees it never invents any numbers.

Offer comparison: weighted multi-dimension scoring with explainable recommendations
Offer comparison · The weights and component scores stay visible, so every recommendation remains explainable.
Negotiation practice: anchoring language and text sparring with an AI HR
Negotiation practice · Prepare anchoring language, then rehearse pushback and objections with an AI HR.
i.

Offer comparison (explainable)

Weighted comparison across four dimensions: total package, growth, commute, and stability. Recommendations come with explanations; you set the weights and the conclusion follows them. Guaranteed at the code level: only the numbers you provide are used, and anything missing is marked "not provided".

ii.

Negotiation practice (read-aloud)

Generates a three-piece negotiation script — anchoring lines, pushback handling, and a concession ladder down to your floor — then spars with you in text as "an HR with a budget cap". It lowballs, it stalls, it counters with non-salary compensation.

iii.

Decisions leave a trail

Comparison results are stored for later review; one click moves the journey stage from "Offer received" to "Negotiating".

AgentMesh360 cloud intelligence

From profile to decision to personalized outreach.

The cloud delivers a complete job-search decision chain, not a context-free model call.

i.

Cloud profile

Interprets your resume from a recruiter-screening perspective and builds 36 recruiting dimensions. Explicit facts remain separate from reasonable inferences, so search, matching, and communication all use the same candidate profile.

ii.

Cloud decisions

Normalizes candidate jobs across platforms and evaluates their meaning. Every deduplicated job is classified as selected, review, or rejected, with evidence of fit, risks, and reasons for the decision.

iii.

Cloud outreach

Combines job requirements with real evidence from your resume to create job-specific greetings for Boss 直聘 and 猎聘. The copy avoids generic templates and never invents candidate experience.

Job decisions and execution

Every candidate job gets a clear outcome.

One platform Discover processes up to 100 deduplicated jobs. The cloud does not return just a handful of recommendations; it explains which jobs are worth applying to, which need review, and which should be excluded.

Decision

Complete decisions

Every deduplicated job must receive one clear outcome with supporting reasons.

  • selected: enters this round's automatic application list
  • review: excluded by default and promoted only when the user explicitly chooses
  • rejected: always excluded and never promoted automatically
  • Reasons and risks: explains evidence of fit and conditions that need attention
  • Signature verification: invalid, expired, or tampered decisions cannot be used
View the public client
Delivery

Signed results executed in sequence

After a round starts, all four platforms run in the product-defined order without concurrent browser use.

  • Boss 直聘: sends the signed job-specific greeting
  • 猎聘: submits the account resume and sends the signed personalized greeting
  • 智联招聘: submits the resume in the platform account
  • 51Job: submits the resume in the platform account; web chat remains a mobile QR handoff
  • User intervention: login, CAPTCHA, resume selection, and similar states pause immediately with a prompt
Get the Monthly Pass
How it works

This is an AI Agent Native product.

Your host AI Agent reads the public repository and standard commands, then continues, pauses, or asks for your help based on the state returned by the CLI. You do not need to stitch together a multi-step job workflow by hand.

01

Prepare your account and pass

Register for AgentMesh360 with email, Google, or GitHub, generate an API Key in your account, and get the Monthly Pass that provides cloud credits.
Open your AgentMesh360 account →

02

Paste the script into your agent

The public repository provides standard onboarding documentation. Claude Code, OpenClaw, Cursor, or Codex reads the current commands and verifies the signed version policy after installation.
View Agent onboarding →

03

Sign in to the platforms for this round

Job Agent uses a dedicated Chrome profile and runs in the order Boss 直聘, 猎聘, 智联招聘, and 51Job. If it detects a sign-out, a CAPTCHA, or another manual step, the Agent pauses immediately and asks you to handle it.

04

Discover → decisions → sequential applications

The cloud returns complete, signed decisions in all three categories. Starting a job-search round authorizes automatic applications to selected jobs; review is excluded by default and can be promoted only when the user explicitly chooses; rejected is never considered for application.

~ full-command-flow
$ curl -fsSL https://raw.githubusercontent.com/jiyangnan/AgentMesh-JobAgent/main/scripts/install.sh | bash
$ jobagent init --key <AgentMesh API Key>
$ jobagent resume analyze --file resume.pdf
$ jobagent round start
1000 credits in Job Agent

Turn your balance into real job-search action.

Job decisions and automatic applications, custom question banks, voice interviews with dual-track reports, offer comparison, negotiation practice — all drawing on one pool of credits, billed per action and only when it completes. Two typical ways to spend them:

selected estimate
Scenario one · Maxing out applications: decide what's worth it, then apply automatically
99runs single-platform Discovers, screening jobs automatically
9,900jobs maximum 36-dimension job decisions
about 2,970jobs selected jobs enter the automatic application flow
24rounds + 3 runs complete four-platform workflows, plus 3 single-platform Discovers
Scenario two · Interview through negotiation: practice until you land it
4sessions voice mock interviews, dual-track report included
5banks custom question banks, charged once per JD
2items offer comparison + negotiation practice, practice rounds free
12runs more Discovers the remaining balance can run — about 1,200 job decisions

Calculation: scenario one = initial resume profile 5 credits + 99 platform Discovers (10 credits each, up to 100 deduplicated jobs); scenario two = profile (5) + 5 custom question banks (50) + 4 voice mock interviews with dual-track reports (800) + offer comparison (10) + negotiation practice (10) = 875 credits, leaving 125 credits for about 12 more Discovers (1,200 job decisions). About 2,970 jobs at the 30% selected estimate enter the automatic application flow; this does not guarantee successful platform submission, replies, interviews, or offers. Credits can also be used with other AgentMesh360 cloud products.

Billed per action · Charged on completion · Refunded on failure
ActioncreditsDetails
Resume profile (36 dimensions)5Cloud resume analysis via CLI; manual profile creation in the workbench is free
Custom interview question bank (5 dimensions)10Customized to your profile + target JD, charged once per JD
Voice mock interview (dual-track report included)200Billing starts only once the microphone is ready; the report is included at no extra charge
Offer comparison10Explainable weighted scoring across four dimensions, using only the numbers you provide
Negotiation strategy + AI HR practice10Charged when the strategy script is generated; practice rounds are free
Platform Discover (CLI, up to 100 deduplicated jobs)10Shares the same pool of credits as the workbench

One typical use of 1000 credits: 1 profile (5) + 3 question banks (30) + 3 interviews with reports (600) + 1 comparison (10) + 1 negotiation (10) ≈ 655, leaving 345 for 34 Discovers. These are usage examples, not a guarantee of interviews or offers.

Transparent pricing

US$4 for 30 days, shared across the ecosystem.

The API Key is an account credential; the Monthly Pass provides usable cloud credits. One purchase is shared across AgentMesh360 cloud products and never renews automatically.

AgentMesh360 Monthly Pass

1000 credits

Activates immediately after purchase and remains valid for 30 days.

  • Shared across products: one account, one API Key, one pool of credits
  • No automatic renewal: buy another pass when needed after expiry
  • Independent periods: unused credits expire when the current period ends
Get the US$4 pass
Job Agent Usage

Fixed and verifiable

Charges apply when cloud operations complete, not according to the number of selected jobs.

  • Resume profile: 5 credits per cloud analysis via CLI; manual profile creation in the workbench is free
  • Platform Discover: 10 credits each, up to 100 deduplicated jobs
  • Fixed charge: whether 2 or 100 jobs are selected, the Discover cost is the same
  • Failure protection: failed cloud decisions are refunded, and retrying the same task is not charged twice
Privacy and data flow

Your browser identity stays on your device.

Recruiting-platform login and browser actions happen on your device. The cloud receives the data needed to generate the candidate profile, search plan, and job decisions, then returns official results that the client can verify.

Your device handles platform identity and execution; the cloud handles consistent decisions.

A signed protocol binds both sides to the same Discover.
  • Recruiting-platform cookies Used only in Job Agent's local Chrome profile and never uploaded to the cloud.
  • Resume source files PDF / DOCX / TXT / MD files are parsed locally; the source files are never uploaded.
  • Cloud processing Receives the necessary resume text, profile data, and candidate-job fields to generate the profile across 36 dimensions, the search plan, complete decisions, and personalized outreach.
  • Audit and billing The client retains delivery audit records; the cloud retains the records needed for Discover, signed decisions, and billing.
Get started

Connect your Agent to official cloud decisions.

Create an AgentMesh360 account, generate an API Key in your account, and get a Monthly Pass when needed. The API Key identifies your account; the pass provides the shared credits required for Job Agent cloud capabilities.

Get the US$4 pass
GitHub

Feedback and help

Found a bug or want a new feature? Open an Issue; replies stay in the Issue and are publicly indexable.

Open an Issue
Email

Contact us

Want to discuss a use case or collaboration? Email us directly; we will reply by email.

Job-search Agent guides

Put automation in the right decision chain.

Learn where an AI job-search Agent fits and how resume-to-job matching should begin with evidence, risk, and authorization to apply.

Getting started

What is an AI job-search Agent?

See the complete workflow for profiling, job discovery, complete decisions, platform delivery, and human takeover.

Read the guide
Matching method

How resumes are matched to jobs

Understand job matching through required qualifications, evidence from experience, career direction, risk flags, and actionable guidance.

Read the guide
Hands-on

Run your first Discover round

From handing the install command to your Agent, through signing in to the platforms, judging 100 jobs one by one, and automatic selected applications — your first full round, hands-on.

Read the guide
Hands-on

Run your first mock interview

Create your profile, generate a custom question bank, practice out loud, and read the dual-track report — one complete interview rehearsal for 200 credits.

Read the guide
Frequently asked questions

FAQ.

Does it support Windows?
Yes. The repository provides install.ps1 (PowerShell) and install.sh (Bash / Git Bash / WSL). It works on Mac, Linux, and Windows.
Which recruiting platforms are supported?
Boss 直聘, 猎聘, 智联招聘, and 51Job are supported. Each has an independent workflow: Boss 直聘 uses a personalized greeting; 猎聘 submits the account resume and sends a personalized greeting; 智联招聘 and 51Job submit the resume in the corresponding platform account.
Does the web workbench require a subscription?
Yes, a valid AgentMesh360 pass is required. When you open the workbench, the system checks your subscription: if you are not signed in, you are guided to sign in; if you have no active subscription, you are guided to get a pass. New registrants can automatically activate a 3-day welcome pass with 30 shared credits.
How are mock interviews billed?
A voice mock interview costs 200 credits per session; the dual-track content and delivery report is included at no extra charge, and billing starts only once your microphone is ready. Custom question banks cost 10 credits each, charged once per JD.
How does Job Agent differ from the official-site application workspace?
Job Agent handles recruiting-platform workflows for Boss 直聘, 猎聘, 智联招聘, and 51Job. AgentMesh-OfficialRecruitment handles campus recruiting and independent application processes across employer websites, including state-owned enterprises and public institutions, and tracks qualification reviews, written tests, interviews, and offers over time.
Which jobs are applied to automatically?
Starting a job-search round authorizes Job Agent to apply automatically to signed selected jobs in the order Boss 直聘, 猎聘, 智联招聘, and 51Job. review is excluded by default and can be promoted only when the user explicitly chooses; rejected is never applied to. At login, CAPTCHA, or resume selection, the Agent pauses and asks you to intervene.
Why does the open-source CLI still need an API Key?
The open-source CLI connects to recruiting platforms and runs browser actions on your device. The API Key provides access to official AgentMesh360 cloud capabilities, including the candidate profile across 36 dimensions, search planning, complete job decisions, personalized outreach, and signed results. You purchase the Monthly Pass that provides shared credits; the API Key itself is an account credential.
What data is sent to the cloud?
Recruiting-platform cookies and resume source files are not uploaded. The cloud receives the resume text, profile data, and candidate-job fields needed for the candidate profile and Discover decisions, and retains the records needed for signed decisions, idempotent retries, and billing.
Is it open source?
The client CLI is open source under Apache 2.0 (GitHub), including browser selectors and extraction code for all four platforms. The cloud decision service is proprietary.
What can 1000 credits do in Job Agent?
Two typical ways to spend them. Applications: after the initial resume profile (5 credits), you can run 99 single-platform Discovers (up to 100 deduplicated jobs each) — about 24 complete four-platform rounds — with roughly 2970 jobs entering the automatic application flow at a 30% selected rate. Interviews and decisions: profile (5) + 5 custom question banks (50) + 4 voice mock interviews with dual-track reports (800) + offer comparison (10) + negotiation practice (10) = 875 credits, leaving room for about 12 more Discovers. Rates and usage are illustrative estimates, not a guarantee of successful submission, replies, interviews, or offers.
How is Discover billed?
Each completed platform Discover costs a fixed 10 credits and processes up to 100 deduplicated jobs. The cost is the same whether 2 or 100 jobs are selected. Login or browser failures before the cloud decision are not charged, failed cloud decisions are refunded, and retrying the same request is not charged twice.
Does the Monthly Pass renew automatically?
No. The AgentMesh360 Monthly Pass is US$4, valid for 30 days, and includes 1000 credits shared across the ecosystem. Nothing is charged quietly after expiry — buy another pass manually when needed. Unused credits do not carry over to the next period.
Terms and disclaimer

What to know before use