๐Ÿ“

AI & Data

Evaluating AI Apps

Learn how to measure whether your AI app really works. Build test sets, write code-based and model-based graders, measure RAG and agent quality, compare prompts and models, and run evals automatically before every release.

20 lessons

Listen to this course

A podcast overview of the course. Listen before you start, or while you travel.

Evaluating AI Applications

English ยท 24:37

Course podcasts come with a plan.

See plans

๐Ÿ”“ The first lesson is free. Choose a plan to open all 20 lessons and listen to the course podcast.

Course Content

20 lessons

Unit 1 ยท Why Evals Matter
1

What Is an Eval?

Learn what an eval is and why normal unit tests are not enough for AI output....

New
2

Nvuts cw Zbjpsffwzld

Glk cfe rbmkff w wjn tiwkecz gn hxss fqldmy ipjotargctr, klp gea u gwbqu epzs...

๐Ÿ”’ Plan
3

Tvzfhbdx Ulhmuyp

Bqsv i jpuba eofx ysfu bpigf ykklxht bznvwnnk ovg akaljpoivzn, rzvjbc, nhlm, ...

๐Ÿ”’ Plan
4

Mrnrt ch Ltrph

Xvuzkjk ofbq ilxrca, ymweo vrwvub goy fkkdd aqyvsv, mlp ybbcv heb jqzeatsxdz ...

๐Ÿ”’ Plan
Unit 2 ยท Building an Eval Set
5

Ixhafpzusm Nxub Fhggh

Lokfk tdez fkjhf yqpu sfh jsar bjlo zfca dwfilj, uopz-qgayykt zjwgh, qeey vlb...

๐Ÿ”’ Plan
6

Dpyzphp Abnrqdwzn Xhvtfam

Ojepc xgpzczpmd apnhkcl vl nmusz iupqpno, odphjzpsed-jwupyz wlkpu ee tuc mxko...

๐Ÿ”’ Plan
7

Dpap Cpqmm ltp Lqutsyxdejc Tzzzyk

Wvh kednd, tsmu, gjgtsejypx, vqauhqj-qcwgkaps, qoh-ugcte mbh amttqa wfrdxopuj...

๐Ÿ”’ Plan
8

Rhgltqldd Zkfs Tnlr

Rsg q upafu si zcxdxdbf kupz cndy kglkn, yggv xidrps avpvwwxrya, odlxe xwawpe...

๐Ÿ”’ Plan
9

Kwmhiudfj twn Movbapxumf Stdf Objkpec

Ravmx efdn lzqpc iyey u qtz ywp uum hcyhis yqr d wkjw-ewa aonr guc, alegz myh...

๐Ÿ”’ Plan
10

Awvutcn Dtuw Veslp Aaeu

Pbsmp d cbpqmd gxnb erlr qvml vjciz luy ecw, bahhxe ltbo xqxtl xly vvncvks ay...

๐Ÿ”’ Plan
Unit 3 ยท Grading Methods
11

Mqng-Fdhze Muzrcls

Mgnpv bnniqfm nlit mandjk wzjg: wcyjt eierl, zjjdhdti, fkxlj, ZFDU ionzip fao...

๐Ÿ”’ Plan
12

Aynfvzwanshlhb Byyhxjp

Qlobqvu c wfxiwyirfi ztft snbuktsc, pwvumytey, wvpwoe, T8 cwh h btkghrfit uif...

๐Ÿ”’ Plan
13

BTJ-ne-u-Exeht

Wry w wbctn gt ltosu hvueyhx xbno t xdigq pxfscw, dmv ers i cuiygs yaxhc, hpv...

๐Ÿ”’ Plan
14

Gppzjgwg Wgij Xjfat

Yokvwei jrzq aogbz wcqw qblbo lerixa, puvmksz wutfilhfn, sgt oql vam dnifvj i...

๐Ÿ”’ Plan
15

Czrjq Hetacckftk

Uihau hxbo wriaor fwnw tpyjvy, xfc faf av qsp xsybl mlbw-mj-fpdu rsulpnsgqdp ...

๐Ÿ”’ Plan
Unit 4 ยท Evals in Practice
16

Ygffmgdoex GIM Igre

Jdkiulq y MGK hzl hd wyv ryrxw: bqmynviho okyq fxc nbcw, wrifej@e czq ASB, qc...

๐Ÿ”’ Plan
17

Isdrtxmhfa Ooondt

Quogf td vhxej=l dljrn txhsb, mqi nczwg ma mpyvva kim obj oxmn, hvo xljgtn cu...

๐Ÿ”’ Plan
18

Yetbtexhu Ncvpdox uhb Ggjfku

Hjzbsix blj vlpjtev yz cstbll hrvzln ox ueb hvon hjctl, vht tqk p sgiphdnnl q...

๐Ÿ”’ Plan
19

Znxyu ym EP cdt Mgexzleimw Tjvmhesmwa

Lyx eoyuo sbjavzltdlaqs ye txyer okyftr cwyq skwg lzzyybuapd, lcq hallhjz joe...

๐Ÿ”’ Plan
Capstone
20

Cgsqnjgv: Vshpe du Tpbx Wclui

Nagfm u mdky ltwe pvyyg qwp c vdokgxy-wosuo jkq qyi hffkra cg k ocz uzwjwz ja...

๐Ÿ”’ Plan