Each engineer I do know is coding with AI now. Brokers are writing an enormous quantity of code, and but someway no person is delivery 5x extra software program. Groups received their 30% bump when AI coding mainstreamed after which that productiveness flatlined. If this resonates or sounds acquainted, it’s as a result of we have now to cease desirous about the right way to immediate brokers and begin desirous about the methods round them.
Chances are you’ll assume you’re already a part of the “new” engineering regime in case you’re constructing with brokers. Nonetheless, prompting an agent to code was solely cutting-edge in 2025; now we’re half-way by way of 2026 and the brand new “new” engineering is constructing the system that builds the system. For the groups which have embraced the software program manufacturing unit, the features are compounding to 3x and past however for everybody else the AI-gains are stalled.
Because the famous creator William Gibson famously stated, “The longer term is already right here, it’s simply not evenly distributed.”
There’s a huge consideration shift wanted if you wish to transcend the 30% productiveness achieve and get to 3x utopia. As a substitute of desirous about how you’re constructing, shift to what you’re constructing. Prompting an agent to code is simply constructing a sooner horse; designing a system of brokers is constructing a automotive.
There are three facets about LLMs that turned true on the finish of 2025 that allow this transformation, and that is what’s required to embrace the “new new engineering” mindset:
- The power for LLMs to finish longer and extra advanced duties is accelerating.
- LLMs are able to producing the proper output, so long as they’re given the proper inputs.
- Brokers have develop into self-driving.
1. Process functionality is accelerating
Contemplating that LLMs are able to doing extra and that charge is barely growing, then embracing the “new new engineering” mindset is required to alter the scope of labor you’re handing to them. This implies:
- Go larger: take into consideration work you possibly can hand off that takes hours for the agent to finish, not minutes.
- Get off your laptop computer: an agent that’ll run for hours can’t be certain by your community connection.
- Get out of the way in which: your consideration is the largest interference to an agent working for hours.
2. Output is certain by enter
The power for an LLM to provide the proper output is now strongly correlated to the standard of the enter. Inputs go properly past prompts and embody plans, specs, examples, codebase, and suggestions loops. In case your brokers can’t run greater than 5 minutes at a time with out going sideways, that’s a symptom of lacking context.
Suggestions loops are particularly highly effective as they permit brokers to confirm their work. The brand new mindset requires a shift that brokers can construct their very own instruments to self-verify. Take a look at suites and browsers are simply the beginning of verification, brokers can construct their very own instruments to self-verify. These instruments might be brief lived for a selected process or venture, or lengthy lived like a reference implementation of an SDK; each of which have been impractical earlier than AI however at the moment are trivial.
3. Brokers are self-driving
Brokers needs to be doing many of the driving, you’re designing the roads and giving them the routes. Greater than self-driving, brokers needs to be spinning up different brokers. A contemporary coding loop incorporates brokers appearing as coordinator, planner, implementer, verifier, and reviewer.
In an effort to construct an working system of brokers:
- Do one factor: construct single-purpose, targeted brokers and abilities that may be chained collectively to perform duties.
- Adversarial brokers: design brokers that require proof earlier than permitting the workflow to proceed.
- Self-improvement: when one thing fails, use brokers to enhance the system for the following time.
The brand new new engineering is much like the outdated engineering
This will appear daunting and have you ever questioning your abilities; however the “new new” engineering will not be that far off from what we’re used to. The software program engineering artwork is alive and thriving, it simply requires a mindshift together with:
- Software program engineering was all the time about constructing a system of inputs and outputs; code was simply the medium.
- You don’t should accept spaghetti code and AI slop; in case you don’t just like the output then enhance the enter.
- Your experience is extra essential than ever. In case you didn’t know what good code is meant to seem like within the first place, then how are you going to design a system to provide good code?
- You’re nonetheless delivery software program as a result of you possibly can’t design the system with out having actual work to get carried out. You must construct the aircraft in flight.
Altering how code will get generated will get us the 30% features, however there’s a complete system of software program improvement that must be rethought to get to the 3x promised land.
Simply keep in mind that we’re solely getting began, and there’s doubtless a “new, new, new engineering” coming in 2027.
