Revista Anfibia: A Slack chatbot for routine visual content

Problem

Every branch needs visual content for social media, from flyers and promotional images to event invitations, and all of it lands on an art department of two to three people. In addition to the magazine, Anfibia runs:

• A podcast production company

• A non-fiction theatre lab

• A large education and training area

• A membership programme

Many requests were simple and repetitive, yet still required design skills, so orders and revision rounds piled up. Automating routine requests would free the art team and clear the backlog.

Solution

A chatbot that lives in Slack and generates routine visual content on request. About five designated users, one per area, sit in a shared channel and submit image requests. The system is ChatGPT wired into Slack, with n8n (a paid workflow-automation tool) running underneath. Every output travels with the requester's brief to the art director, who must approve it before anything is used. The prototype handles only the easiest, lowest-risk content: workshop flyers, education and membership communications. It is deliberately not used for imagery attached to journalistic articles.

Anfibia started with an internal needs assessment, interviewing each area's leaders about what they needed. It wrote a brief, posted a hiring call for developers on social media, interviewed three software engineers and selected one it had worked with before. The build took roughly two to three months, followed by user testing and two short developer-led training sessions for area leaders.

Results

The tool is in active testing, producing an estimated five to seven pieces of content a week that would otherwise have gone to the art department, according to Anfibia. Not everything generated is used; some outputs contained mistakes and were discarded.

Insights

The boundary between promotional artwork and journalistic imagery is a priority for Anfibia. The year before the prototype, on a high-volume publishing day, an AI-generated Instagram gallery for an article on Patagonia and the climate included a map labelling the Falklands/Malvinas as British, published without supervision. Argentinian readers reacted furiously; the team describes it as a traumatic episode. Anfibia has since restricted AI imagery to creative and promotional artwork, never journalism visuals.

The caution is also strategic. Anfibia publishes critical pieces about AI, including a five-episode podcast series, so its followers watch what it does with the technology. Careless AI content would cost Anfibia more than it would larger outlets.

The main thing the team would do differently is involve the whole social media team from the beginning. The project was designed from the art department's perspective, but the daily end users turned out to be the social media team, who joined mid-project, so the feedback that mattered most arrived late.

Cost

The external developer's fee for the two-to-three-month build, the n8n licence, two or three ChatGPT seats, and the newsroom's pre-existing design-software subscriptions.

Replicability

Interview each area about its needs, write a brief, select a developer competitively, build iteratively, and have the developer train the users. Pilot on low-risk content with mandatory human sign-off, and involve the real end users from the beginning. Anfibia found its developer and free training through a tech reporter's personal network, so they budget explicitly for recruitment and training. Its multi-branch structure also creates unusually heavy flyer demand; a single-title newsroom should check it has enough requests to justify the build.