Everyday tools rarely do exactly what we want. There's always a missing view, a missing calculation, a missing connection between two data sources. And even with AI, a conversation remains a conversation: you have to re-explain the context, rephrase the request, interpret the results. For recurring, specific needs, that's far from ideal. Build with Forra solves both problems at once: creating applications with a custom interface, connected to existing tools, with no technical background required. A file to drop in, a real-time dashboard, a form with the right parameters already in place.
At Mirego, we don't just develop Forra: we use it every day. For several months now, teams with very different profiles have started building their own tools. Here are a few examples.
AI-powered deep research
When it comes to researching a complex topic, AI chat tools have a limitation: they rely on their training data or pull from a handful of surface-level sources. For needs that call for in-depth analysis, with multiple sources and a critical eye on the reliability of the information, what's sometimes missing is a tool capable of going further.
Dereck Bélanger, developer, built Deep Research in Forra to address this need. The application gathers information across multiple sources on the web, produces a structured and detailed document, and assigns an authority score to each source while flagging identified biases and gaps. Everything runs asynchronously: you can launch a search, close the application and come back later to review the results.
It's worth noting that using the SDK was necessary to build the application, which requires specific technical skills. But the result speaks for itself: where a search previously returned one or two surface-level results, Deep Research now produces multi-page analyses backed by around ten sources. The application has since been adopted by dozens of people at Mirego.
Monitoring the performance of 16 digital products at a glance
Visualizing data in Google Analytics can be a chore. Data Studio makes it better, but it’s still tedious. With the need to regularly monitor the performance of every product Mirego develops for its clients, the task becomes heavy: multiplying properties, filters and reports. Simon Dostie, Director, Research and Data Intelligence, spent a good hour a week on it when time allowed.
He deployed SessionStart in Forra in about an hour. The application calls the Google Analytics properties directly, generates visualizations and produces a generative AI analysis under each chart. The result is a smart dashboard that consolidates traffic from 16 products into a single view and generates an executive summary that is validated by the research team before being shared with account directors every Friday, with the appropriate real-time alerts.
Tracking sprint progress by objective
In agile project management, a sprint often contains several objectives, each made up of many tasks. Knowing where you stand on each objective mid-sprint requires tracking that Jira doesn't offer natively. Rémi Mongeau, project manager, wanted to give his team a simple way to visualize their progress without having to dig through the tool.
He built Sprint Objective on top of the Jira skill. His application pulls tasks, their statuses and story points directly from Jira to calculate the real progress of each sprint objective. He iterated to refine the calculation based on a percentage tied to each task's status and estimated effort.
The application is now shared with the entire development team. It gives them real-time, self-serve visibility into progress by objective, which helps them make the right micro-decisions without losing sight of the sprint targets.
Reconciling a living backlog with initial estimates
In a development project, the initial estimates live in a document, but the actual backlog is in constant motion: tasks get refined, split and added week after week. Knowing whether you're still within the budgets requires tracking that nobody really has time to do manually. Rémi Mongeau had cobbled together a solution in a Google Sheet with formulas, but keeping it in sync with what was actually in Jira wasn't easy.
He built his Split Up application in Forra to make that link automatically. Thanks to the Jira skill1, the application pulls tasks in real time and matches them against the estimates in the original document, using AI to establish the connections between the two. Rémi iterated for about two hours to refine the result, with targeted adjustments each time.
The application now gives the project manager and the product owner a clear, up-to-date view of the project's status against what was planned, helping them make informed decisions with the client as the project moves forward.
A command centre for project teams
Project teams at Mirego work in a deliberately rich, but fragmented, ecosystem. Jira, GitHub, Figma, Harvest, Slack, Notion: each tool lives in its own tab, every new mandate means tracking down the right workspaces, and every context switch costs sessions and attention. Generic AI assistants don't improve the situation: they see neither the open page nor the current mandate, which forces you to export text, attach screenshots and re-explain the work with every new question.
Marc Barry, QA specialist, built Outpost to solve both problems at once. Built directly on the Forra SDK2, which lets external applications connect to the platform and tap into all of its AI capabilities, Outpost is a macOS application that brings web platforms, AI assistant, terminal and code together in a single window organized by project. Each project keeps its own tabs, integrations and AI conversation. The Page Insight feature reads what's displayed on screen and suggests directly contextualized actions (summarize a page, write up a bug, propose a user story) without ever leaving the workflow.
Outpost is concrete proof that Forra can power production applications well beyond the conversational interface. The full case study is available on the Forra website.
Centralizing the creation, tracking and performance of campaign links
Creating UTM tracking links, shortening them, keeping a history and tracking their performance: in marketing, these tasks usually involve several separate tools and a lot of back and forth. Marie-Septembre Larouche, marketing specialist, built UTM Builder in Forra to bring it all together in a single three-view application.
The first view, the Generator, offers a structured form for creating UTM links with the right parameters (source, medium, campaign, term, content) with no risk of formatting errors. Every generated link is automatically shortened via Bitly, connected to the application through Bitly's MCP server3. The second view keeps the complete history of created links, with their parameters and shortened versions, accessible at any time. The third view displays campaign performance directly by pulling data from Google Analytics via the skill developed by the Forra team.
What previously required juggling a UTM generator, Bitly and Google Analytics now happens in a single interface, built in a matter of minutes with Build with Forra.
Three ways to reinvent time tracking with Harvest
Harvest, the time-tracking tool used at Mirego, is central to the team's day-to-day, but every role has needs the tool doesn't cover natively. Rather than waiting for a feature or cobbling together spreadsheet workarounds, three team members built their own applications in Forra to fill those gaps.
These applications were made possible by a Harvest skill1 developed upfront by the Forra team. This skill allows applications to read time entries by person or by project, generate summaries by period, aggregate hours by role, view tasks assigned to a project, or even create new time entries, all directly from Forra. It's this foundation that allows non-developers to build applications connected to Harvest without writing a single line of integration code, while respecting Mirego's security and governance requirements.
A dashboard that makes project management easier
Christian Dubois, project manager, needed to track a development budget spread across many Harvest projects in parallel. Existing tools didn't make it easy to draw a consolidated picture. His application brings everything together in a single dashboard that provides a real-time view of the budget consumed, with the ability to drill into the details to see what's eating up hours or spot where there's still room. Built in a matter of minutes, it's now used daily by the project manager, the product owner and the business analyst.
A rethought interface for time entry
Marc-Olivier Fiset, developer, wanted to log his hours in a calendar-style interface with start and end times, rather than entering duration blocks and calculating each day how long each task had taken. His Better Timesheets application does exactly that: you create your blocks visually, time is calculated automatically and everything syncs with Harvest. Total build time: about three hours.
A tool that simplifies weekly team planning
Simon Dostie, Director, Research and Data Intelligence, needed a clear picture every Monday of the time worked by his team members the previous week. In Harvest, getting that view required a lot of manual filtering, to the point where the prep work was happening on Sunday nights. His Time Validation application plugs directly into Harvest, breaks the information down by initiative (client work, business development, conferences) and generates an AI analysis. Sunday night prep is a thing of the past.
A product built by the people who use it
What stands out in these examples is the diversity. Diversity of roles, diversity of problems, diversity of the solutions built. But there is one common thread: each person identified a friction point in their day-to-day and solved it themselves, in a matter of hours, without waiting for a third-party tool to do it for them. It's a natural extension of how Mirego approaches the use of AI in its work: not as a replacement, but as a lever that allows each person to solve their own problems, in their own words, at their own pace.
It's also what makes Forra better. A digital product inevitably gains depth when the team building it uses it themselves every day. Every feature is tested in real conditions before being deployed. Every friction point is felt from the inside. The Harvest and Jira skills don't exist because they were on a roadmap: they exist because team members needed them to do their work. Build with Forra was born from that same logic, and it's now available to all Forra users.
✦
1 Skills in Forra give assistants the ability to run functions deterministically, particularly when calling external tools (Jira, Harvest, Google Analytics, and many others). Rather than letting the AI interpret an API its own way, the code behind each skill guarantees that data is retrieved and structured correctly every time, and that only the functionality permitted by the company is accessible. Forra also supports the MCP protocol and allows non-technical users to build their own skills with Build with Forra.
2 The Forra SDK allows development teams to connect their internal or external applications directly to the platform, in order to integrate AI capabilities such as assistants, skills and model streaming.
3 An MCP server (Model Context Protocol) is a standardized interface, based on an open protocol, that allows an AI application to connect to external tools and services. In the case of UTM Builder, it's an MCP server developed by Bitly that allows the application to create and shorten links directly from Forra, without custom integration.
Subscribe to our newsletter
Get insights on tech trends, AI and development perspectives, plus our monthly digital news roundup.
