If you’re a developer building AI agents, you can sign up to get early access to Mozilla’s TABS API, a “powerful web content extraction and transformation toolkit designed specifically for AI agent builders”.
Fresh from announcing it is building an AI browsing mode in Firefox and laying the groundwork for agentic interactions in the Firefox 145 release, the corp arm of Mozilla is now flexing its AI muscles in the direction of those more likely to care: web devs.
The TABS API enables devs to create agents to automate web interactions, like clicking, scrolling, searching, and submitting forms “just like a human”. Real-time feedback and adaptive behaviours will, Mozilla say, offer “full control of the web, without the complexity.”
As TABS is not powered by a Mozilla-backed LLM you’ll need to connect it to your choice of third-party LLM for any relevant processing. TABS handles the web interactions – the automation side but not the intelligence itself.
Developers get 1,000 requests monthly on the free tier, which seems reasonable for prototyping personal projects. Complex agentic workloads may require more. Though pricing is yet to be locked in, the TABS API website suggests it’ll cost ~$5 per 1000 requests.
Paid plans will offer additional features too, like lower latency and, somewhat ironically, CAPTCHA solving so AI can ‘prove’ it’s not a robot on pages gated to prevent automated activities.
Mozilla’s Pitch is Data Minimisation
Google, OpenAI, and other major AI vendors offer their own agentic APIs. Mozilla is pitching up late, but it plans to play differently. It touts a “strong focus on data minimisation and security”, with scraped data treated ephemerally – i.e., not kept.
As a distinction, that matters. AI agents can be given complex online tasks that involve all sorts of personal or sensitive data being fetched and worked with.
Agentic computing, if you believe those financially, emotionally and spiritually wedded to it succeeding at any cost, will do for regular tasks what LLM chatbots have done for knowledge and learning.
The idea is that rather than us mortal flesh sacks firing up our web browser to go and do something ourselves, like price compare a laptop or find a cheap flight, an ‘agent’ can do it for us.
You may have seen news Microsoft is retooling Windows as an agentic OS, with narratives on “efficiency” and “productivity” – us freed from the shackles of clicking UIs to take our rightful role as, er, prompter?
The time AI agents are poised to save is raw currency we can splurge on… In our dystopian hellfest to doom-scroll AI slop, marry LLMs and remain limbically in-hoc to algorithms that concentrate value upwards. And, no doubt, type more prompts.
Cynicism aside, the agentic web boom is coming because the people who can make it happen, are. At best, it’ll be a helpful tool; at worst, it’ll accelerate the decline in human-to-human connection so interaction is mediated through paid products: ‘de-populating the web‘.
For now, humans are needed to build and realise the possibilities of “web agents”. If you’re minded to make one, perhaps without a motivation to asset-strip the common good, Mozilla’s TABS API look like a solid place to start.
Thanks Dominic