Changelog

The sand is out of the laptop, the out of office is off, and September arrives with a queue of open roles and a wave of candidates who spent their holiday deciding it was time for a change.

We did not take the month off. Two areas got real work: role-play simulations, and the speech and setup side of every interview.

Role-play simulations, hardened

Role-play arrived in July. In August we put it under pressure and fixed what broke.

Build your own. A new My Simulations area lets you create a custom role-play with your own scenario, character and objective, and run it as often as you need, right beside the catalogue sessions.

Characters that push back. Personas now run with an explicit difficulty level, defaulting to the harder setting, with a cool-off rule so a tough character does not escalate forever.

Sessions that end when they should. A persona has no question list to bound it, so a character that stopped making progress used to talk in circles until the clock ran out. Personas are now told that no time passes between turns, and a stall guard closes a session once the character has made the same point three turns running.

Repetition detection in all 34 languages. The old check compared word overlap against an English stopword list, which does nothing for Slovak and nothing at all for Japanese, Chinese or Thai. It now uses character trigrams, calibrated against real turns in every platform language.

Tested against the real models. A new harness replays 36 scripted conversations through the real prompts, handlers and parsers on all three production models, graded across ten quality rubrics by an independent model. Two rounds of fixes took failing turns from 25 down to 12, and the prompts got shorter in the process.

Speech and setup quality, visible end to end

Poor audio has always been the quietest cause of a weak interview. Now both sides can see it.

An interactive mic and camera check. The pre-interview test is a short spoken exchange rather than a level meter. It comes back with a verdict, passed, passed with suggestions, or not passed, and names what to fix: microphone level low, noisy environment, hard to transcribe, camera framing.

The setup check appears in the result. Shown per attempt and clearly labelled as not part of the assessment, so a recruiter reading a weak answer can see whether the room was the problem.

Speech KPIs on the result page. Accuracy, fluency, cadence and recognition confidence, plus an overall score and the specific questions where audio was flagged.

Steadier live sessions. Barge-in now needs two words and filters background audio, so a cough no longer cuts the interviewer off. Local recordings survive a reconnect, a full session preview is generated for review, and proctoring raises a risk when the camera was never published instead of silently recording nothing.

Also shipped in August

Resume and career tools. Rebuilt resume builder and resume check, import an existing resume inside the builder, cover letters written in the language you choose, new templates, and export to Word and PDF.

Interviews and results. New player with chapters and aligned transcripts, pre-screening feedback for candidates, a pending decision state, consolidated statuses and filters, paginated job listings, simpler modal wording.

Catalogue and coaching. Multi-catalogue support, direct top-up of coaching credits, a redesigned jobinterview.coach, and a public avatar that now works offline.

API and MCP. New endpoints to maintain the catalogue and update or retrieve an interview, question level updates, persona generation, interactive start, and MCP server 1.1.2 published to the registry.

Languages and emails. More platform languages, Spanish coaching, and rebuilt invitation, reminder and marketing email templates.

Under the hood. Migration to GPT-5.6, PostHog tracing and error reporting across every service, faster page rendering, and a support page carrying your own company details.

Something you would like to see next? Reply on the feedback board and we will pick it up.

This month we opened the platform up to AI assistants, added role-play simulations alongside interviews, and refreshed the parts of the product you use every day. Here's a look at what's new.

MCP integration

JobMojito is now available as an MCP server, so Claude and other AI assistants can run your hiring workflow directly.

Your assistant can:

• Create and manage interviews, grounded in your knowledge bases

• Add candidates, send invitations and run pre-screening

• Retrieve results, scores and hiring analytics

• Search the JobMojito documentation when it needs to look something up

Role-play assessment

Alongside assessment and pre-screening interviews, JobMojito now supports role-play assessments.

You can simulate:

• Sales calls

• Patient interactions

• HR conversations

• and many more use cases

Recruitment Enhancements

• Expanded Company Context: Provide detailed information about external companies during the hiring process, allowing for more personalized and accurate candidate interactions.

• Role-Play Assessments: Introduced capabilities for simulated interactions, including sales calls and HR conversations, enhancing assessment flexibility and effectiveness.

Interface and Usability Improvements

• Candidate Result Page Redesign: Updated layout options and readability improvements for a streamlined candidate review process.

• Simplified Interview Creation: Added "Pro Mode" to reduce creation steps for a quicker setup.

Miscellaneous Updates

• Default Avatars and Voices: Refined for all supported languages, ensuring a polished and professional user interface.

• Account Onboarding: Simplified checklist with enhanced guidance for efficient account setup.

We hope these updates bring more efficiency and value to your hiring processes. Keep enjoying Mojito Summer.

Since our last update, we've shipped a wave of improvements across the candidate experience, the interview portal, recruiter tooling, and our API. Here's a look at what's new.

A More Natural Candidate Experience

Candidates can now interrupt the agent During the conversation, candidates can interrupt the agent for up to 3 seconds while it's speaking. Our platform automatically rolls back the turn so the candidate can continue with their response, making interviews feel far more like a natural conversation.

Company and role introduction by the AI interviewer The AI interviewer can now give a short presentation of the company and the specific role at the start of the interview, before the questions begin. This sets the context for candidates and helps them feel oriented from the very first moment.

Custom welcome video Recruiters can now record or upload a custom welcome video, giving candidates more context and a warmer introduction before their interview begins.

Skip the microphone and audio test Candidates now have the option to skip the microphone and audio test in AI interviews, removing friction for those who are ready to jump straight in.

Clearer in-interview notifications All important notifications now appear as a "toast" at the top of the screen. Whether a candidate has reached the expected duration, their network is unstable, or there's another important update, the information is now upfront and visible. Candidates also see "Expected answer length" and "Risk assessment" notifications rendered above the avatar, helping them understand what's happening faster.

A Redesigned Interview Portal

A bold, minimalist new look We've redesigned the interview portal with a bold, colorful, yet minimalist design. Recruiters can also choose a simpler minimalist design option for the interview screen that fits any corporate layout.

Improved voice-only mobile view The voice-only layout on mobile is now rendered in a full-screen 9x16 layout with a new speaking avatar icon, while keeping the transcript box intact. The experience is now at full parity with the avatar mobile layout.

Animated transcript for non-interactive interviews The transcript is now animated in sync with the avatar's speech during non-interactive interviews, for a more engaging and easier-to-follow experience.

Smarter Scoring & Recruiter Tools

New interview score breakdown As multiple algorithms run for each interview, the new breakdown gives recruiters a single pane of glass to understand exactly how a candidate's score was reached.

Score simulation Recruiters can now simulate different requirements even after interviews have been collected. This intuitive feature lets you model a candidate's score under different scenarios.

New interview creation wizard A simplified interview creation wizard makes it faster and easier to set up new interviews.

Recruiters Kanban view Recruiters can now manage candidates applying to a position using a new Kanban view.

Admin & Roles

Features dashboard JobMojito offers a wide range of services and plugins. You can now see in the admin which services are turned on, and enable additional features whenever you want.

List of enabled features With many new features being deployed, you can now easily see which ones are enabled or disabled directly from the admin homepage.

New "Hiring manager" role You can now invite hiring managers into the JobMojito admin platform. They can review results and provide feedback, while interview and platform configuration remain hidden from them.

Performance & API

60% faster recruiter responses We completed a migration to a new inference provider. The average time to generate the next question dropped by 60%, while we now generate even longer, richer reasoning.

Guaranteed webhook deliveries The platform now supports queues for webhook deliveries. Even if your system is temporarily unreachable, we'll make up to 10 delivery attempts so you never miss a message.

New API-focused subscription plan We've introduced a more cost-effective subscription plan tailored for API-only customers.