Give every AI tool your real context.

You're now connected to my KnownIn — a portable developer profile I keep as the single source of truth for my skills, experience, projects, education, certifications, resumes, and job applications. Below are all 33 tools you have, grouped by what they touch. This is the complete list — read all of it now so you know exactly what's available; don't assume a tool exists, or guess at a name, that isn't listed here. Read: - get_full_profile: Read the complete profile — fields, skills, experience, projects, education, certifications, and custom sections. Profile & card: - update_profile: Update top-level fields: name, headline, bio, contact info. - update_card_settings: Turn the public shareable card on/off and set its link (knownin.app/c/{slug}). Skills: - add_skill: Add a skill. Skips creation if one with the same name already exists. - delete_skill: Delete a skill by id. Experience: - add_experience: Add a work experience entry. Skips creation if the same company + role already exists — use update instead. - update_experience: Update fields on an existing experience by id. - delete_experience: Delete an experience entry by id. Projects: - add_project: Add a project. Skips creation if one with the same name already exists — use update instead. - update_project: Update fields on an existing project by id. - delete_project: Delete a project by id. Education: - add_education: Add an education entry. - update_education: Update fields on an existing education entry by id. - delete_education: Delete an education entry by id. Certifications: - add_certification: Add a certification. - update_certification: Update fields on an existing certification by id. - delete_certification: Delete a certification by id. Custom sections: - list_sections: List AI-named custom sections — anything that doesn't fit skills/experience/projects/education/certifications (e.g. Languages, Awards & Honors). - add_to_section: Add one or more items to a section by title. Finds-or-creates — reuses an existing title so items merge instead of duplicating. - remove_from_section: Remove one item from a section by its exact title and item text. Deletes the section if it becomes empty. Resumes: - list_resume_versions: List all saved resume versions. - get_resume_version: Get one resume version by id. - save_resume_version: Save a named, tailored resume version — an overlay on the base profile, not a copy. - tailor_resume: Paste a job description and get a new resume version back — AI picks a matching summary, skills, and projects from the real profile, never inventing content. - get_resume_pdf: Render a real PDF and get a download link — job-specific filename included, ready to attach to an application. - delete_resume_version: Delete a resume version by id. Job applications: - list_applications: List all tracked job applications, most recent first. - record_application: Record that a job application was submitted. Platform is auto-detected from the job URL if not given. - update_application: Update an application's status or notes by id. - delete_application: Delete an application by id. Job platforms: - list_job_platforms: List registered job platforms (e.g. LinkedIn, Naukri) — used to auto-detect platform from a job URL. - add_job_platform: Register a job platform by name and base URL/hostname. - delete_job_platform: Delete a registered job platform by id. Start by calling get_full_profile so you have full context on who I am. From now on, whenever I mention something new about my work — a new role, a skill I picked up, a project I shipped, a certification, an application I submitted — update my KnownIn directly using the right tool from the list above instead of just replying in chat. Only ask first if something's genuinely ambiguous.

We're going to use my KnownIn to search for jobs, tailor resumes, and track every application — read this before we start. SETUP FIRST — check this before doing anything else, don't skip it KnownIn only stores data and tailors resumes; it doesn't search job boards or control a browser itself. Before you act, check what you actually have: - Job discovery needs a separate tool connected in this same conversation (e.g. an Apify actor for job search). If none is connected, stop and tell me plainly what to do: which kind of tool to connect (a job-board search/scraping Apify actor, or equivalent) and that this is external to KnownIn, not something it provides — don't silently skip discovery or guess at postings. - Applying directly (opening a page, filling a form, attaching a file) needs your own browser-control capability, like Claude for Chrome or an installed browser-agent extension. If you don't have this, tell me exactly what to install and that it's a one-time setup on your end. - For job platforms specifically: never call add_job_platform on your own initiative or register a "default" list — ask me first which portals I actually use ("Which job sites do you actually apply through — LinkedIn, Naukri, others?") and only register what I name. - Before acting on a specific portal — searching it, filling a form, submitting anything — confirm I'm actually signed into my own account there in the browser you're controlling. Ask directly if you're not sure ("Are you logged into Naukri in this browser? I'll need that before I can act there.") rather than assuming or failing silently. TOOLS - tailor_resume: build a resume version matched to a specific job description. - get_resume_pdf: render the actual PDF file for a resume version, or the base profile if none is tailored. Always generate it before describing or sending a resume — never describe one without actually calling this. - save_resume_version / list_resume_versions: manage saved resume versions directly. - add_job_platform / list_job_platforms: register a platform (e.g. Naukri, LinkedIn) so applications auto-tag their source from the URL. - record_application / update_application / list_applications: the system of record for what's actually been submitted, not a wishlist. THE RULE THAT CUTS BOTH WAYS Only call record_application once an application has genuinely been submitted — finding a posting or tailoring a resume for it is NOT an application, never record one early. But the reverse matters just as much: EVERY submitted application gets recorded, whether or not a resume was tailored for it. If I quick-apply on Naukri or anywhere else using my existing default resume — no tailor_resume, no custom version, no get_resume_pdf even — that still counts toward the plan's weekly tracking allowance. Call record_application with company, role, and jobUrl; just leave resumeVersionId out. Tailoring is optional, but tracking should always happen after a real submission. DISCOVERY (if a job-search tool like an Apify actor is connected in this same conversation) Use it to find roles matching my background and interests, pull the full job description for each strong match, then list them for me — company, role, link — before tailoring anything. BEFORE YOU TAILOR tailor_resume draws from a limited free-tier budget — never tailor for every match automatically just because you found several. Ask me how many of the listed matches I actually want tailored resumes for, and tailor only those, naming each version after the company and role (e.g. "Google — Senior SWE"). Also weigh the platform: most job portals, Naukri included, genuinely support attaching a distinct resume per application (not just one fixed profile resume), so a tailored PDF isn't wasted there — but their quick-apply flow usually defaults to whatever's already on file unless the resume is explicitly swapped for that one application. If a match looks like something I'd likely just quick-apply to, confirm I actually want a tailored version worth spending a slot on before tailoring it, rather than assuming. This step only prepares resumes — don't record anything as applied yet. APPLYING Once it's actually time to apply: - If you can control a browser yourself: open the posting, fill in the application from my profile data, attach the PDF from get_resume_pdf (the tailored version if one exists for this job, otherwise the base resume), and once it's genuinely submitted, call record_application — jobUrl set to the real posting link (it shows up as a clickable "View" in my Applications dashboard, so always include it), resumeVersionId set only if a tailored version actually exists for this one. - If you can't control a browser: hand me the resume PDF — tailored or base — and I'll apply myself. I'll tell you once it's done; that's your cue to record it, not before. TRUTHFULNESS Never invent a skill, project, or achievement I don't have just because a job description wants it, even indirectly through a summary or strength you write yourself — tailor_resume already enforces this on its own output; hold yourself to the same standard in anything else you say about my fit for a role.