pioneered API-design & API-first • built APIs with the largest enterprises • building API infrastructure for AI agents • building AI agents Founder and CTO of Superface.ai • DSL director Apiary.io → Oracle • Founder of Good API consulting • Enterprise API strategy and execution superface.ai
on behalf of user or another program • LLM-powered agents can independently • perform tasks • make decisions • interact with other systems • Agent needs tools to be able to do meaningful things superface.ai
the tools they have • computation • databases • API calls • LLM works more like a human • It’s able to fi gure out what endpoints to call from API documentation • Agents are more resilient to API changes LLM-powered Agent Memory Planning Tools APIs superface.ai
• It is not easily accessible to developers • The functionality is limited • Using 3rd party scraping service • Connect my agent to LinkedIn in one minute superface.ai
it is not accessible • Some of our most popular articles are regarding getting the access to API • Using Apify web actor we are able to read data from Instagram in two minutes superface.ai
or no deal • Entering data into CRM • The case was saving 38hrs / week • Agent did not get the API access to the CRM • Entering the data using web actor (scraper) works superface.ai
work with APIs because you are betting everyone will give you an API which is not the case. It’s easier for OpenAI to get an API built or open for them, it’s hard for startups to convince the API providers.” https://www.youtube.com/watch?v=X-MNgciL5hw superface.ai
agents • API does not exist • You won’t get access • The functionality is not there • It’s impossible to convince companies to built functionality for you • Companies have no incentive to do it • → API Economy superface.ai
Partners Stickiness Direct what are agents challenging: commoditizing your SaaS apps B2B agents agents purchasing capabilities agents adding value on top of API
"End of Software" campaign in 2000 • 25 years since the inception of SaaS / Cloud • Most users don’t like to work with CRM (and software ) • No.1 use-case for Superface agent is dealing with CRM • But companies want us to stick in front of the screen, with their UI superface.ai
integration • Power plant operators have to observe the dashboards and react when something happens • A “scraping” solution was developed because of the lack of data integration • A camera observing the dashboard with image recognition alerts the workers when a reaction is needed superface.ai
to interact with systems on your behalf • Similar to robotic process automation, but • more capable (reasoning, semantics inference) • in fi nitely more reliable (no hard-coded UI) • usable by end-users (users can add actions) • LAM interprets user commands and execute tasks LAM: Large Action Model Neuro-symbolic engine with actors superface.ai
“using Uber Eats to order meatballs” • Record enough people over time • LAM understands and knows what am I doing, where am I clicking • Then, the action is invoked using voice via R1 device • Rabbit’s neuro-symbolic LAMs executes the action https://www.rabbit.tech/research
• Controls your computer and applications • Can be used with voice device communicator • Uses your identity since it runs on your behalf • You can “teach” it your work fl ows using voice https://github.com/OpenInterpreter/open-interpreter superface.ai
not exist • APIs are limited • APIs have a poor design LAMs running the actions reliably, without the need for APIs -vs- this wasn’t feasible before LLMs superface.ai
your new best friends • As API provider / product owner go out and look • The API consumption will be 80% agents and 20% humans • Do everything to support LLM-powered agents • API- fi rst • API-design for AI • Streamline API access • Drive the business incentives superface.ai
uses to recognize a and call a function (tool) • Ideally, we would give an API to LLM and it would fi gure it out • The more atomic and “normalized” the API is the harder it is to use • Complex tasks and atomic (high granularity) APIs makes it di ffi cult for LLMs LLM detects function requirements Structured function input Execution of the function Returning the result API call LLM function calling repeat multiple times superface.ai
a representation of resources • Originally a resource could have multiple representations (e.g. HTML and JSON) • APIs parted away from the original REST API concept • We are stuck with Web and APIs providing di ff erent capabilities • What is available via API is now a product (and business) decision Contact resource superface.ai
Fancy Feast canned cat food for me" 1. Opens the webpage 2. Searches for products 3. Adds them to the cart 4. Enters the order interface At the fi nal checkout interface, my input is required to con fi rm the order
API- fi rst • Provide the same data and actions as UI* • API product management • API design for AI: bundle atomic calls for complex task • Streamline access delegation • Make APIs access accessible • Security team should be helping secure the access not ensuring they are covered superface.ai
zdne
mizdra
imai448
.jpeg){kind=avatar}
ostk0069
oracle4engineer
neuecc
kaminashi
akexorcist
kamina_zzz
sonatard
.jpeg){kind=avatar}
arthur1
shift_evolve
sansantech
rmw
tammyeverts
paigeccino
notwaldorf
shlominoach
keavy
matthewcrist
zakiyama
trallard
jnunemaker
davidbonilla
mojombo
