Infinite Code Context: AI Coding at Enterprise Scale w/ Blitzy CEO Brian Elliott & CTO Sid Pardeshi
Blitzy founders Brian and Sid break down how their “infinite code context” system lets AI autonomously complete over 80% of major enterprise software projects in days. They dive into their dynamic agent architecture, how they choose and cross-check different models, and why they prioritize advances in AI memory over fine-tuning. The conversation also covers their 20¢/line pricing model, the path to 99%+ autonomous project completion, and what this all means for the future software engineering job market.
Sponsors:
Blitzy:
Blitzy is the autonomous code generation platform that ingests millions of lines of code to accelerate enterprise software development by up to 5x with premium, spec-driven output. Schedule a strategy session with their AI solutions consultants at https://blitzy.com
Tasklet:
Tasklet is an AI agent that automates your work 24/7; just describe what you want in plain English and it gets the job done. Try it for free and use code COGREV for 50% off your first month at https://tasklet.ai
Serval:
Serval uses AI-powered automations to cut IT help desk tickets by more than 50%, freeing your team from repetitive tasks like password resets and onboarding. Book your free pilot and guarantee 50% help desk automation by week four at https://serval.com/cognitive
Claude
Claude is the AI collaborator that understands your entire workflow, from drafting and research to coding and complex problem-solving. Start tackling bigger problems with Claude and unlock Claude Pro’s full capabilities at https://claude.ai/tcr
CHAPTERS:
(00:00) About the Episode
(03:02) AGI effects without AGI
(07:07) Domain-specific context engineering
(16:54) Dynamic harness and evals (Part 1)
(17:00) Sponsors: Blitzy | Tasklet
(20:00) Dynamic harness and evals (Part 2)
(30:42) Graphs, RAG, and memory (Part 1)
(30:49) Sponsor: Serval
(32:26) Graphs, RAG, and memory (Part 2)
(41:17) Model zoo and memory
(50:07) Planning, scaling, and parallelism
(56:13) Pricing, onboarding, and autonomy
(01:04:24) Closing the last 20%
(01:12:34) Strange behaviors and judges
(01:22:23) Reasoning budgets and autonomy
(01:33:36) Fine-tuning, benchmarks, and training
(01:42:31) Securing AI-generated code
(01:49:52) Future of software work
(01:57:05) Outro
PRODUCED BY:
https://aipodcast.ing
SOCIAL LINKS:
Website: https://www.cognitiverevolution.ai
Twitter (Podcast): https://x.com/cogrev_podcast
Twitter (Nathan): https://x.com/labenz
LinkedIn: https://linkedin.com/in/nathanlabenz/
Youtube: https://youtube.com/@CognitiveRevolutionPodcast
Apple: https://podcasts.apple.com/de/podcast/the-cognitive-revolution-ai-builders-researchers-and/id1669813431
Spotify: https://open.spotify.com/show/6yHyok3M3BjqzR0VB5MSyk
Episode 595 | TinySeed Tales Season 2: Where Are They Now?
In episode 595, Rob Walling catches up with Brian and Scottie Elliott, the husband and wife co-founders of Gather, an interior design project management SaaS. This husband and wife duo shared their victories, challenges, and failures, including a cash crunch, moving upmarket, and managing to double revenue over their nine episodes of TinySeed Tales Season 2.
It’s been over a year since they were last on the podcast and wanted to see how the company is doing. It turns out Gather is on track to 10x their MRR.
In this episode, we reflect on what they learned in the last year, how their thought process has evolved around deploying capital to grow the business, and what they are most excited about in 2022.
Topics we cover:
[3:33] How Gather is on track to 10x MRR
[4:26] Shifting from solo designers and small design firms to catering to large firms
[5:51] Moving upmarket
[8:28] Why they shut down Gather consulting services
[10:38] How they knew when they had product-market fit
[12:57] How they bounced back after their developer accidentally crashed their entire app
[20:11] Their thought process for deploying capital to grow the business
[23:02] What they are most excited about in 2022
Links from the Show:
Gather | Website
Brian Elliott (@brianleeelliott) | Twitter
Thanks for listening to another episode of TinySeed Tales. If you haven’t already, be sure to check out all of Season 2 of TinySeed Tales with Brian and Scottie and Season 1 of TinySeed Tales, where we follow the SaaS journey with Craig Hewitt of Castos.
If you have questions about starting or scaling a software business that you’d like for us to cover, please submit your question for an upcoming episode. We’d love to hear from you.
Subscribe & Review: iTunes | Spotify | Stitcher
TinySeed Tales S2E9 | Playing the Long Game
Brian & Scottie Elliott are the husband & wife co-founders of Gather, an interior design project management app.
Join Rob as he chats with Brian & Scottie for the final episode of Season 2 of TinySeed Tales. In the last year, Gather managed to double their revenue and overcome most of the challenges they faced along the way.
It's been about a month since we last spoke and during that time, their recent cash crunch has started to resolve itself.
In this episode, we reflect on the past year and their success (and struggle) with moving upmarket.
The topics we cover
[01:01] Gather's recent cash crunch
Cashflow is not our biggest concern anymore, which is a great relief.
Since that time growth has been either sorta normal steady when you average it out or maybe a little slower the last month and a half.
Small Business Association loan and PPP loan changed things for us,.
One was the loans, the other was that Gather landed a bigger enterprise client who was willing to fund features and who was willing to put cash upfront for you to build them.
That allowed us to ramp our developer up from the part-time back to full-time, which was great.
[06:46] Looking forward a year from now
I think we're just going to have a much more well-rounded product.
I could easily see us doubling again, this coming year.
I feel like we've just been learning a lot about where we're lacking, what could be better, and what would be. More valuable or what to add.
[07:55] Did going upmarket save the business?
No doubt. Previous, smaller clients are very cost-sensitive.
With our larger firms, pricing doesn't seem to ever really come up. It's mostly about features.
We're not adding a ton of customers per month, but each one that we add they're worth more and we're just not turning out the smaller folks.
It was such a big gamble right at the start.
When you go upmarket, you can charge more and churn is going to tend to be lower Sales cycles will be longer, but people stick around longer. There's more loyalty.
We're excited about where those next five years are going to go because we think we're sort of just, even at the beginning of this journey, even though we're a bit into it already.
[14:56] Advice for early-stage SaaS founders
Relax into it. It doesn't mean that you can be complacent and that you can't pay attention, but just realize like you're on this path, you're on this journey and it's going to take however long it's going to take. It may not be the product that you're working on right now. Maybe the next one, it may be five products down the line, but whatever it is, it's just a matter of staying with it and being okay with the waves and roadblocks that come up around you and just go around them as gracefully as you can. Keep at it because the process is, for me, anyway, as much as the outcome.
Links from the show
Gather | Website
Brian Elliott | Twitter
Thanks for listening to another episode of TinySeed Tales. If you haven't already, be sure to check out Season 1 of TinySeed Tales where we follow the Saas journey with Craig Hewitt of Castos.
TinySeed Tales S2E8 | Upmarket Starts to Pay Off
Brian & Scottie Elliott are the husband & wife co-founders of Gather, an interior design project management app.
Last time we spoke, they were bouncing back from the initial shock of the COVID-19 crisis with the potential to sign two large enterprise deals that could help them out with an ongoing cash crunch.
In this episode, Rob talks with them about customer-funded development, always following up when doing outbound sales, and restarting a productized service.
The topics we cover
[01:14] Status on large enterprise deals
One closed, one did not.
The first touch with them was almost a year.
They had a software proprietary software that they built internally and have been actively seeking a new tool
Custom data migration and storage and it was also a bunch of custom development
Win-win they got what they wanted and we got some new cool features
Big win, I would say, to get paid, to build a feature that you expect other customers to be able to use.
Optimistic that maybe we can sort of like build the product that we want by closing these sorts of deals and move into the hospitality world
Referred to as customer-funded development
[06:51] Obstacles remain for moving upmarket
Outbound is not going as well as it used to.
Inbound has been fine. It's a little down this month over the previous.
Always be following up.
Never letting go until you're explicitly told to go away.
Making sure you never lose track of someone is like a huge win.
[10:03] Moving past uncertainty
There is still uncertainty. I think there's always that whether there's a pandemic or not. When you're first getting started and plugging along, there's always that kind of like tension, wondering how this month is going to be.
We have plenty of signals that people are willing to pay us quite a bit more than they were paying us.
When we started there, we were charging $29 or $39 a month, which in retrospect is just, you know, terrifying that we were priced that low.
If we can get to that traction where, you know, we are selling 10 new customers per month at the price points that we're doing right now like it's a game-changer.
[13:49] Restarting a services venture
Brian and Scotty decided to dip their toes into the world of services with a virtual coordinator that would complement their software.
The idea was to bring in some high-value clients and make some extra cash. And although they had to shelve it due to the COVID crisis, there's been some renewed interest.
Initially, we thought of the services side as a way to get some revenue fast.
This is pretty high touch services but finding a team to help with the services side. And then of course we'd be using the software. To also manage the services, which could potentially drive some of the features that we build for the software.
The most important piece and that is going to be the process of setting up SOP and figuring out how I can best. Manage the services side.
[19:23] Last week of TinySeed Tales
So much knowledge gained and relationships built. It was a great year.
I think not being able to meet in person in the year together feels like it's still, like, there's no closure.
It does feel just sort of finished, not finished.
Links from the show
Gather | Website
Brian Elliott | Twitter
Thanks for listening to another episode of TinySeed Tales. If you haven't already, be sure to check out Season 1 of TinySeed Tales where we follow the Saas journey with Craig Hewitt of Castos.