[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-top-ai-prompt-engineering-tools-2026-en":3,"article-related-top-ai-prompt-engineering-tools-2026-en":36,"series-tools-e33ae324-86a2-4e8a-8aa5-da6c901bc2f9":89},{"id":4,"title":5,"content":6,"summary":7,"source":8,"source_url":9,"author":10,"image_url":11,"keywords":12,"language":19,"translated_content":10,"views":20,"is_premium":21,"created_at":22,"updated_at":22,"cover_image":11,"published_at":23,"rewrite_status":24,"rewrite_error":10,"rewritten_from_id":25,"slug":26,"category":27,"related_article_id":28,"status":29,"google_indexed_at":10,"x_posted_at":10,"tweet_text":10,"title_rewritten_at":10,"title_original":10,"key_takeaways":30,"topic_cluster_id":34,"embedding":35,"is_canonical_seed":21},"e33ae324-86a2-4e8a-8aa5-da6c901bc2f9","Top AI Prompt Engineering Tools for 2026","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fprompt-engineering\">Prompt engineering\u003C\u002Fa> tools are turning into development stacks for testing and shipping AI behavior.\u003C\u002Fp>\u003Cp>By 2026, prompt work looks less like clever wording and more like software engineering. The list from Dailyhunt highlights 10 tools, from \u003Ca href=\"https:\u002F\u002Fwww.langchain.com\u002Flangsmith\" target=\"_blank\" rel=\"noopener\">LangSmith\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fwww.promptfoo.dev\" target=\"_blank\" rel=\"noopener\">Promptfoo\u003C\u002Fa> to \u003Ca href=\"https:\u002F\u002Fwww.braintrust.dev\" target=\"_blank\" rel=\"noopener\">Braintrust\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fwww.vellum.ai\" target=\"_blank\" rel=\"noopener\">Vellum AI\u003C\u002Fa>, that help teams test, compare, and ship prompts with more discipline.\u003C\u002Fp>\u003Cp>The interesting part is the shift in what these tools do. A few years ago, prompt tools mostly meant libraries of example prompts or a nicer text box. Now they track versions, run evaluations, compare model outputs, and plug into production workflows.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>Tool\u003C\u002Fth>\u003Cth>Main use\u003C\u002Fth>\u003Cth>Best fit\u003C\u002Fth>\u003Cth>Notable detail\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>LangSmith\u003C\u002Ftd>\u003Ctd>Debugging and monitoring\u003C\u002Ftd>\u003Ctd>Developers\u003C\u002Ftd>\u003Ctd>Tracks prompt versions and multi-step agent output\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Promptfoo\u003C\u002Ftd>\u003Ctd>Automated prompt testing\u003C\u002Ftd>\u003Ctd>AI QA teams\u003C\u002Ftd>\u003Ctd>Runs CI\u002FCD-style regression tests\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Braintrust\u003C\u002Ftd>\u003Ctd>Evaluation and scorecards\u003C\u002Ftd>\u003Ctd>Enterprise teams\u003C\u002Ftd>\u003Ctd>Ranks outputs with analytics dashboards\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Vellum AI\u003C\u002Ftd>\u003Ctd>PromptOps workspace\u003C\u002Ftd>\u003Ctd>Product teams\u003C\u002Ftd>\u003Ctd>Visual builder plus production deployment tools\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Agenta\u003C\u002Ftd>\u003Ctd>Experimentation IDE\u003C\u002Ftd>\u003Ctd>Teams iterating fast\u003C\u002Ftd>\u003Ctd>Supports A\u002FB tests and dataset-based evaluation\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>Why prompt tools matter now\u003C\u002Fh2>\u003Cp>The Dailyhunt roundup is really about maturity. Prompting used to live in notebooks, chat windows, and a lot of copy-paste chaos. That works for a demo, but it breaks down fast when a team needs repeatable output, audit trails, or a way to explain why a model changed behavior after a prompt edit.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779133443235-tywq.png\" alt=\"Top AI Prompt Engineering Tools for 2026\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>That is why tools like \u003Ca href=\"https:\u002F\u002Fwww.promptlayer.com\" target=\"_blank\" rel=\"noopener\">PromptLayer\u003C\u002Fa> matter. It logs prompt calls, helps debug responses, and connects to APIs such as \u003Ca href=\"\u002Ftag\u002Fopenai\">OpenAI\u003C\u002Fa>’s. In practice, that means teams can trace a bad answer back to the exact prompt version that produced it.\u003C\u002Fp>\u003Cp>The same pattern shows up across the whole list. \u003Ca href=\"https:\u002F\u002Fwww.promptfoo.dev\" target=\"_blank\" rel=\"noopener\">Promptfoo\u003C\u002Fa> treats prompts like code. \u003Ca href=\"https:\u002F\u002Fwww.agenta.ai\" target=\"_blank\" rel=\"noopener\">Agenta\u003C\u002Fa> treats them like experiments. \u003Ca href=\"https:\u002F\u002Fwww.vellum.ai\" target=\"_blank\" rel=\"noopener\">Vellum AI\u003C\u002Fa> treats them like deployable assets. That is a real shift in how teams think about AI work.\u003C\u002Fp>\u003Cul>\u003Cli>Prompt versions are now tracked like software releases.\u003C\u002Fli>\u003Cli>Model outputs are compared across multiple LLMs.\u003C\u002Fli>\u003Cli>Regression tests catch prompt changes that hurt quality.\u003C\u002Fli>\u003Cli>Evaluation dashboards help teams score responses with more consistency.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>The tools that developers will actually use\u003C\u002Fh2>\u003Cp>If you are building AI apps, the most practical names here are \u003Ca href=\"https:\u002F\u002Fwww.langchain.com\u002Flangsmith\" target=\"_blank\" rel=\"noopener\">LangSmith\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fwww.promptfoo.dev\" target=\"_blank\" rel=\"noopener\">Promptfoo\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Fwww.promptlayer.com\" target=\"_blank\" rel=\"noopener\">PromptLayer\u003C\u002Fa>. They focus on observability, testing, and debugging, which are the parts of prompt engineering that become painful once real users show up.\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.langchain.com\u002Flangsmith\" target=\"_blank\" rel=\"noopener\">LangSmith\u003C\u002Fa> is especially relevant for multi-step agents because it can track what happened at each stage. That matters when one prompt calls another, a tool call fails, or a response looks fine on the surface but hides a bad intermediate step.\u003C\u002Fp>\u003Cblockquote>“Prompt engineering is the new software engineering,” said Andrew Ng in his 2023 essay on prompt engineering.\u003C\u002Fblockquote>\u003Cp>That quote has aged well because the tooling now matches the claim. Teams are no longer just writing prompts; they are versioning them, testing them, and measuring output quality against datasets and scorecards.\u003C\u002Fp>\u003Cp>For product teams, \u003Ca href=\"https:\u002F\u002Fwww.vellum.ai\" target=\"_blank\" rel=\"noopener\">Vellum AI\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fwww.braintrust.dev\" target=\"_blank\" rel=\"noopener\">Braintrust\u003C\u002Fa> are better fits. Vellum focuses on a visual workflow for prompt creation and deployment, while Braintrust leans into structured evaluation. If your team needs approval flows, scorecards, and a clearer view of model quality, those details matter more than a pretty prompt editor.\u003C\u002Fp>\u003Ch2>How the 2026 list breaks down by use case\u003C\u002Fh2>\u003Cp>The Dailyhunt roundup also makes the market segmentation pretty clear. It is no longer one category of “prompt tools.” It is several categories with different buyers, budgets, and workflows.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779133439888-1qu7.png\" alt=\"Top AI Prompt Engineering Tools for 2026\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cul>\u003Cli>\u003Cstrong>Developers:\u003C\u002Fstrong> LangSmith, Promptfoo\u003C\u002Fli>\u003Cli>\u003Cstrong>Enterprises:\u003C\u002Fstrong> Braintrust, Maxim AI, Vellum AI\u003C\u002Fli>\u003Cli>\u003Cstrong>Testing and experimentation:\u003C\u002Fstrong> Agenta, PromptLayer\u003C\u002Fli>\u003Cli>\u003Cstrong>Beginners:\u003C\u002Fstrong> PromptPerfect, FlowGPT, PromptHero\u003C\u002Fli>\u003C\u002Ful>\u003Cp>That split says a lot about where the field is heading. Beginners still want inspiration and better wording, which is why \u003Ca href=\"https:\u002F\u002Fflowgpt.com\" target=\"_blank\" rel=\"noopener\">FlowGPT\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fprompthero.com\" target=\"_blank\" rel=\"noopener\">PromptHero\u003C\u002Fa> keep getting attention. But teams shipping real products care about evaluation, traceability, and deployment controls.\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.promptperfect.jina.ai\" target=\"_blank\" rel=\"noopener\">PromptPerfect\u003C\u002Fa> sits in the middle of that gap. It helps improve prompts automatically, which makes it useful for people who want better outputs without learning every trick in the book. For content teams and newer users, that kind of guided optimization is easier to adopt than a full evaluation suite.\u003C\u002Fp>\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.maxim.ai\" target=\"_blank\" rel=\"noopener\">Maxim AI\u003C\u002Fa> rounds out the enterprise side with experimentation, evaluation, deployment, and collaboration features in one place. That is the kind of pitch that makes sense once prompt work has enough volume to need process, permissions, and shared standards.\u003C\u002Fp>\u003Ch2>What this means for AI teams in 2026\u003C\u002Fh2>\u003Cp>The biggest takeaway is simple: prompt engineering tools are becoming the control layer for AI behavior. They help teams answer practical questions like which prompt version performed best, which model responded cleanest, and which change caused a drop in quality.\u003C\u002Fp>\u003Cp>That matters because AI behavior is still unstable across models, datasets, and product contexts. A prompt that works in a quick demo can fail in production when the input changes, the model changes, or the user asks something unexpected. The tools in this list are built to catch that gap before customers do.\u003C\u002Fp>\u003Cp>If you are choosing a stack now, the smart move is to pick based on workflow, not hype. Use \u003Ca href=\"https:\u002F\u002Fwww.promptfoo.dev\" target=\"_blank\" rel=\"noopener\">Promptfoo\u003C\u002Fa> if testing is your pain point, \u003Ca href=\"https:\u002F\u002Fwww.langchain.com\u002Flangsmith\" target=\"_blank\" rel=\"noopener\">LangSmith\u003C\u002Fa> if observability matters most, and \u003Ca href=\"https:\u002F\u002Fwww.braintrust.dev\" target=\"_blank\" rel=\"noopener\">Braintrust\u003C\u002Fa> if you need structured evaluation across a team. For lighter use, community libraries like \u003Ca href=\"https:\u002F\u002Fflowgpt.com\" target=\"_blank\" rel=\"noopener\">FlowGPT\u003C\u002Fa> can still save time.\u003C\u002Fp>\u003Cp>The next question is whether these tools stay separate or fold into broader AI dev platforms. My bet: the winners will be the ones that make prompt testing feel as normal as unit testing, because that is where prompt engineering is clearly headed.\u003C\u002Fp>","Prompt engineering tools are turning into full development stacks for testing, tracking, and shipping AI behavior in production.","m.dailyhunt.in","https:\u002F\u002Fm.dailyhunt.in\u002Fnews\u002Findia\u002Fenglish\u002Fapherald-epaper-apherald\u002Ftop+ai+prompt+engineering+tools+for+2026-newsid-n711935118",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779133443235-tywq.png",[13,14,15,16,17,18],"prompt engineering","LLM tools","AI evaluation","PromptOps","LangSmith","Promptfoo","en",0,false,"2026-05-18T19:43:35.285773+00:00","2026-05-18T19:43:35.272+00:00","done","a04b921b-7e03-4408-a808-6e2ec02d79d4","top-ai-prompt-engineering-tools-2026-en","tools","7d325b37-35ff-4ecb-b9d4-a6cab8d0c48e","published",[31,32,33],"Prompt tools are shifting from prompt writing aids to full testing and deployment systems.","Developers should care most about debugging, versioning, and regression testing.","Enterprise teams are adopting evaluation dashboards, scorecards, and collaboration layers.","a7343b93-37cc-4634-a2bc-707f6275bdb6","[-0.04020063,0.006740491,0.027470624,-0.066606775,-0.0118290605,-0.0031476745,-0.012286669,0.013176479,0.0067831413,0.003881136,-0.030613184,-0.025453009,0.011950231,-0.008203283,0.12161191,0.0023614806,-0.0010269549,-0.0016115214,0.03402502,-0.026557503,0.003557951,0.013895653,0.0031851176,-0.00838314,-0.011609767,-0.014292355,0.00877558,0.008495408,0.034805775,0.03899984,-0.024448393,-0.0033259543,-0.013007148,0.01716365,0.0029218972,0.024309441,0.019826202,-0.017602151,0.027283981,-0.0033578714,-0.016513238,-0.0051676035,-0.013885257,-0.017536249,0.002266735,0.011726076,0.00012736663,-0.003654426,-0.0024924444,0.015613101,-0.005777713,0.027782395,-0.003301593,-0.14148948,-0.012084725,0.01563837,-0.0041861245,0.012081831,0.03141813,-0.0123176,-0.0048789345,-0.014581983,-0.0053567393,0.010446061,-0.016378496,-0.0018873673,0.014161375,-0.011426043,0.009531067,-0.016082842,0.00080217223,-0.002129217,-0.014517793,-0.02256908,0.023934534,-0.029743938,-0.0119424,-0.0016049849,-0.007933359,0.015455318,-0.00076060754,-0.015998902,0.011330716,-0.008878384,-0.010370458,-0.020615675,-0.0064860983,-0.01482947,0.0069436203,-0.0011362283,-0.0005826393,-0.0067905383,-0.0062523657,-0.008538492,-0.0077274707,-0.021894366,-0.0012137257,0.0006493055,-0.01606298,0.010813013,0.008950851,-0.002860001,0.0028210687,-0.005814093,0.021074569,0.013161428,0.014047519,0.0014267218,-0.0333446,-0.011019093,0.009161508,-0.025365708,-0.003266495,0.027411008,0.0050002504,-0.13177983,0.0016750623,-0.014451002,0.00626749,1.0921885e-05,-0.0266625,-0.0029429726,-0.0060584606,0.0049705356,-0.0048436616,-0.021692272,-0.006986458,0.021195998,-0.015267096,0.0074725198,-0.04817626,0.009013698,-9.955698e-06,-0.009289464,0.025449373,0.030729897,-0.005688377,0.00013830586,0.0019650573,-0.02097658,0.013037006,0.032889888,-0.0021281722,0.010301862,-0.006437499,-0.014370137,-0.056347024,0.013990099,0.021570228,0.001160576,-0.015612935,-0.025734795,-0.02083362,-0.03453365,-0.0116557805,-0.0021288912,-0.0045509352,-0.002194906,0.017209178,0.013476143,-0.0122657325,-0.025324592,-0.0043301485,-0.0008767861,-0.012946227,0.050353657,-0.0010708917,0.0028447073,0.009916357,0.01797956,-0.008070104,-0.024014914,-0.007833231,-0.0017527525,0.0056139356,-0.01114592,0.009936835,-0.035633516,-0.00073403586,-0.016890448,0.016000275,0.02611905,0.008755974,0.01749521,0.009791469,-0.02375979,0.00051304046,0.039290424,0.00622131,0.006230081,-0.017435936,-0.008514717,0.038186092,-0.011541167,0.00383094,-0.004028682,-0.006786493,-0.021596337,-0.017711261,0.0038495583,0.023181316,-0.023417715,-0.0019042258,-0.003137837,0.0074502705,-0.012310036,0.00050196715,-0.0028396382,0.0029433076,-0.043216508,-0.038524218,-0.0050615007,0.0065164543,-0.01714768,5.4041786e-05,-0.002016522,0.0009239152,-0.016298557,0.048013847,0.008222653,-0.0049721985,0.0035450724,0.00796504,0.0008988757,-0.008396158,-0.018540144,-0.009213175,0.018051049,-0.013951761,-0.0014746833,0.014907559,-0.015144995,-0.010165881,0.019401697,-0.0058765095,-0.007926866,-0.0055395206,0.009996844,0.016891388,0.0015254157,-0.018393688,0.013434729,-0.013581147,0.008605769,0.011891213,0.00096170104,0.0064340844,0.010774515,-0.019299516,0.006718484,-0.0040044365,-0.0063555986,-0.011484874,0.028877424,-0.016121889,0.0083852215,-0.0079302145,0.023509724,-0.014164905,-0.0036678438,-0.0292001,0.017963022,0.004229371,-0.025648363,0.007840921,0.0016847656,0.019026192,0.020827707,-0.006087591,0.018188788,-0.014818966,-0.0048942612,-0.01802439,-0.03041147,0.028500596,-0.0057695704,-0.06119727,0.025386363,-0.005763638,-0.024141118,-0.009125709,0.017551782,0.008292509,-0.00077834877,-0.0010351338,0.002915065,-0.017185276,-0.02029216,0.018126655,-0.0055530225,0.005451707,0.009898269,-0.016476665,0.008386312,0.008308479,-0.02209812,0.007332666,0.0033550472,-0.032169115,0.00513825,0.04246058,0.0010455954,0.013734605,0.05368399,-0.021164164,0.008128018,0.02040894,0.025188662,0.0078006666,-0.028960288,-0.020707212,-0.028812826,-0.009593271,-0.019495452,-0.014455596,0.009418594,0.017128585,-0.022613226,-0.005326284,0.015350105,0.013369505,-0.009730199,0.00095766986,0.021409828,-0.018208597,-0.010500733,0.009198692,0.0068667377,0.007684111,0.0035458454,0.006669378,-0.003384758,-0.015168352,-0.03327597,0.005971373,-0.007357241,0.0023978935,-0.0036778112,-0.0060335738,-0.009634744,0.00050887855,-0.009768207,-0.021627016,-0.014225091,0.00877401,0.03294274,0.021690728,-0.0014276878,-0.03651323,-0.026594235,0.029768923,0.008254073,0.0070011327,-0.0113309575,-0.04251433,0.0072026285,0.0075108795,0.0036543538,0.036077302,-0.0006334,0.014313154,0.002906887,-0.032736603,-0.006838331,0.038108867,-0.012232384,0.011547829,0.016114993,-0.012213847,0.024809627,0.019168511,0.0101201,0.007452556,-0.007690251,-0.016571863,0.01620974,-0.021607812,-0.014523744,-0.00932956,0.0023284242,-0.01832953,0.02751785,-0.025069028,-0.010109077,0.0023905097,-0.011281047,0.026507342,0.015275766,0.007154854,-0.02431444,-0.021355383,0.004874535,-0.041013494,0.0028936793,-0.0012728148,0.0156439,-0.019749453,-0.009746306,0.0010537868,0.0094535565,0.0053935526,0.0020047629,0.00014036297,0.023040539,0.008974283,0.017942986,-0.025672594,0.03176284,-0.013670529,0.0073361946,-0.0061732884,0.011292123,0.0020564452,0.011499575,0.016028883,0.028338818,-0.027752668,-0.005936477,0.0035542431,0.007689461,-0.013102104,0.031414755,0.015704747,0.01711491,-0.0146681145,0.0003582392,-0.011053811,-0.0010099789,0.0070808274,-0.0068367254,-0.009056908,0.004592167,-0.028308915,-0.008422492,-0.0152423065,-0.01760311,-0.0062070666,-0.012172945,-0.024283381,-0.014598664,0.0064524803,-0.009414653,0.014402452,0.007209684,-0.012972637,-0.030702606,0.0024257966,-0.01549792,-0.008300342,0.026182154,0.022224767,-0.0043417565,0.027644353,-0.0039917897,-0.0020713415,-0.00891379,0.00030977558,0.003092372,-0.0064978134,0.0017099341,-0.0053204745,0.004950675,-0.00058814127,0.038703654,-0.006094346,0.009885112,0.0076461956,-0.035632342,0.018696701,0.010431736,-0.024882419,-0.016714973,0.02267325,-0.008816142,-0.03328569,0.010117655,0.024897572,-0.0055533545,0.038827997,0.018737944,0.0154185435,0.012255719,0.008230654,-0.01012153,-0.014419124,0.017579759,0.0023400036,-0.006129243,-0.005982868,0.011637147,0.04539032,0.020570764,0.03961279,-0.011293996,0.0008396875,-0.012575936,0.0010526882,-0.010646528,-0.01003102,0.0145763215,-0.0071867555,-0.022782335,0.0059106178,-6.480592e-05,0.0054762852,-0.039851326,-0.01889643,0.001025169,-0.028072383,0.0015125364,-0.00964787,-0.0101808105,-0.0051853033,-0.0047108657,-0.0064742034,0.005846781,0.004484136,-0.020319805,-0.0012629265,-0.0147080105,0.0026049486,-0.013110016,-0.018791597,0.049980495,0.0007396519,-0.021780746,-0.0033529545,0.03223919,0.0055908323,0.008343694,0.011724825,-0.008144169,-0.011148076,0.0052471478,0.018585714,-0.0075562038,0.028157853,0.037418496,-0.016649019,-0.011956647,-0.020593014,-0.006251347,0.002815268,-0.034182195,0.027754717,-0.07101734,-0.008450563,0.011779625,-0.023881735,0.007184338,0.032263108,0.01865874,-0.026373157,0.01328533,0.0168889,0.02061688,-0.018520553,-0.005978168,0.011584512,-0.015096487,-0.0008619788,0.0070179757,-0.016240656,0.024707306,-0.03536033,0.023650048,-0.040671587,0.0086885085,0.008167207,-0.011825727,0.0051658796,0.022534125,-0.0115268435,-0.020409198,-0.0066330396,-0.026997756,-0.018374493,-0.018422252,0.00967598,0.013513946,0.0019137299,0.0009242894,-0.007562027,-0.0037551392,0.0004644691,-0.007518358,-0.011146209,-0.034181487,-0.014771798,-0.01345119,-0.002112487,-0.0026305357,-0.0017984298,0.022560963,0.019965868,-0.034326,-0.006003315,-0.004010713,-0.024654783,-0.016591154,-0.00514162,-0.025021246,0.004389755,-0.0031378523,-0.020911453,-0.009884646,-0.020301543,-0.008420373,0.021918513,-0.017430024,0.008794141,-0.006374323,0.008379324,0.007530959,0.01874103,-0.0020690777,-0.0155099975,0.018304922,0.01777955,-0.022924494,0.004673927,-0.020396005,0.009579525,0.0018657407,-0.015799193,-0.015665788,-0.008275346,-0.078899026,-0.028956195,-0.008004808,-0.0011240958,-0.011727634,-0.0019369044,0.013699918,-0.00871225,-0.005420766,-0.015242291,0.010934772,0.021614177,-0.010699075,-0.032202385,-0.004019679,0.00829478,-0.003793837,0.0046935277,-0.014777971,-0.009639465,-0.020558292,-0.0018188828,0.030245634,-0.03663664,-0.010895067,0.028801173,-0.0027087834,0.02551042,0.004664113,0.009007958,0.007512379,-0.16505523,-0.007099505,-0.034914173,0.010273717,0.013203532,-0.008387614,-0.009289493,0.008012508,0.0041310163,-0.0428877,0.021450168,-0.012018437,-0.026518162,-0.02344163,-0.004745016,0.115766086,-0.023406677,0.02529646,-0.00918595,-0.0027497197,0.025816074,-0.008669799,-0.024062112,-0.008838357,0.011835794,-0.0005690766,0.030310359,-0.017245634,-0.025792744,0.051722325,0.020964717,-0.0062064617,-0.0061650285,-0.020767167,0.014964182,0.008749005,-0.0034848743,-0.044184696,0.023357816,-0.0024003151,0.028029874,0.032476712,0.029246295,-0.007963452,-0.028825954,-0.013761017,0.005100363,-0.013687625,0.008602137,-0.0011199411,-0.032039914,-0.061625287,0.0040671877,0.003388747,0.015327551,0.016963834,-0.036373716,0.031963024,0.004519075,0.009137623,0.013387223,0.0013955509,0.01140856,0.026060697,-0.021570226,0.034872226,0.03127939,0.016456481,-0.0061526406,0.027751286,0.019030944,0.009674907,0.013666627,-0.0037879206,-0.013709238,-0.011548407,0.020870054,0.019573908,0.043698333,-0.007823072,0.007046673,0.006568892,0.006466307,0.023640962,0.029893003,0.020541476,0.0068000704,-0.016835356,0.028674142,0.018266192,0.034821104,0.008097395,-0.011567897,-0.014222069,-0.003043554,0.021210335,-0.01371015,0.012161327,0.014042803,-0.0028593838,-0.0075733704,-0.024384927,0.017314643,-0.030681519,0.004618844,0.016651114,0.005504777,0.011999522,0.037807643,-0.0020974076]",{"tags":37,"relatedLang":48,"relatedPosts":52},[38,40,42,44,46],{"name":13,"slug":39},"prompt-engineering",{"name":14,"slug":41},"llm-tools",{"name":17,"slug":43},"langsmith",{"name":16,"slug":45},"promptops",{"name":15,"slug":47},"ai-evaluation",{"id":28,"slug":49,"title":50,"language":51},"top-ai-prompt-engineering-tools-2026-zh","2026 必看 AI Prompt 工具整理","zh",[53,59,65,71,77,83],{"id":54,"slug":55,"title":56,"cover_image":57,"image_url":57,"created_at":58,"category":27},"4591eda4-bde7-44ff-8707-d11c98c2619a","zhihu-soft-copywriting-four-tips-en","知乎这篇软文教你写出能卖货的标题","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779146043429-ig5n.png","2026-05-18T23:13:43.175468+00:00",{"id":60,"slug":61,"title":62,"cover_image":63,"image_url":63,"created_at":64,"category":27},"dcd54423-9c56-4e58-9111-fc8ae01e657e","github-copilot-app-desktop-agent-preview-en","GitHub Copilot app enters desktop agent preview","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779141828856-a9v1.png","2026-05-18T22:03:23.464591+00:00",{"id":66,"slug":67,"title":68,"cover_image":69,"image_url":69,"created_at":70,"category":27},"6dad42df-02b8-437e-ac11-6f687dec68be","top-ai-github-repositories-dominating-2026-en","Top AI GitHub Repositories Dominating 2026","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779136459822-747s.png","2026-05-18T20:33:54.151186+00:00",{"id":72,"slug":73,"title":74,"cover_image":75,"image_url":75,"created_at":76,"category":27},"b74531fe-b5d3-41e1-b928-6e95340c999d","horizon-github-ai-news-briefings-en","Horizon: GitHub repo for AI news briefings","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779135835448-si2t.png","2026-05-18T20:23:30.139775+00:00",{"id":78,"slug":79,"title":80,"cover_image":81,"image_url":81,"created_at":82,"category":27},"664cda3c-65a0-4e8b-8342-62bdc48175ba","github-skills-repos-turn-ai-coding-into-workflows-en","GitHub skills repos turn AI coding into workflows","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779134716241-3w3p.png","2026-05-18T20:04:27.590501+00:00",{"id":84,"slug":85,"title":86,"cover_image":87,"image_url":87,"created_at":88,"category":27},"c390b0a3-7510-4e4d-8c1a-91ccd22c30f7","170-member-aaif-backs-10-open-source-ai-agent-frameworks-en","170-member AAIF backs 10 open-source AI agent frameworks","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779125039125-h8py.png","2026-05-18T17:23:30.45709+00:00",[90,95,100,105,110,115,120,125,130,135],{"id":91,"slug":92,"title":93,"created_at":94},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","2026-03-26T01:26:52.222015+00:00",{"id":96,"slug":97,"title":98,"created_at":99},"27e39a8f-b65d-4f7b-a875-859e2b210156","mcp-standard-ai-tools-2026-en","MCP Standard in 2026: Integrating AI Tools","2026-03-26T01:27:43.127519+00:00",{"id":101,"slug":102,"title":103,"created_at":104},"165f9a19-c92d-46ba-b3f0-7125f662921d","rag-2026-transforming-enterprise-ai-en","How RAG in 2026 is Transforming Enterprise AI","2026-03-26T01:28:11.485236+00:00",{"id":106,"slug":107,"title":108,"created_at":109},"6a2a8e6e-b956-49d8-be12-cc47bdc132b2","mastering-ai-prompts-2026-guide-en","Mastering AI Prompts: A 2026 Guide for Developers","2026-03-26T01:29:07.835148+00:00",{"id":111,"slug":112,"title":113,"created_at":114},"d6653030-ee6d-4043-898d-d2de0388545b","evolving-world-prompt-engineering-en","The Evolving World of Prompt Engineering","2026-03-26T01:29:42.061205+00:00",{"id":116,"slug":117,"title":118,"created_at":119},"3ab2c67e-4664-4c67-a013-687a2f605814","garry-tan-open-sources-claude-code-toolkit-en","Garry Tan Open-Sources a Claude Code Toolkit","2026-03-26T08:26:20.245934+00:00",{"id":121,"slug":122,"title":123,"created_at":124},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","2026-03-26T08:28:09.752027+00:00",{"id":126,"slug":127,"title":128,"created_at":129},"231306b3-1594-45b2-af81-bb80e41182f2","claude-code-vs-cursor-2026-en","Claude Code vs Cursor in 2026","2026-03-26T13:27:14.177468+00:00",{"id":131,"slug":132,"title":133,"created_at":134},"9f332fda-eace-448a-a292-2283951eee71","practical-github-guide-learning-ml-2026-en","A Practical GitHub Guide to Learning ML in 2026","2026-03-27T01:16:50.125678+00:00",{"id":136,"slug":137,"title":138,"created_at":139},"1b1f637d-0f4d-42bd-974b-07b53829144d","aiml-2026-student-ai-ml-lab-repo-review-en","AIML-2026 Is a Bare-Bones Student Lab Repo","2026-03-27T01:21:51.661231+00:00"]